Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Graph-based input representation.
Articles de revues sur le sujet « Graph-based input representation »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleurs articles de revues pour votre recherche sur le sujet « Graph-based input representation ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les articles de revues sur diverses disciplines et organisez correctement votre bibliographie.
1
Lu, Fangbo, Zhihao Zhang et Changsheng Shui. « Online trajectory anomaly detection model based on graph neural networks and variational autoencoder ». Journal of Physics : Conference Series 2816, no 1 (1 août 2024) : 012006. http://dx.doi.org/10.1088/1742-6596/2816/1/012006.
Texte intégralRésumé :
Abstract To efficiently determine whether an entire trajectory exhibits abnormal behavior, we introduce an online trajectory anomaly detection model known as GeoGNFTOD, which employs graph neural networks for road segment representation, creating a directed graph by mapping trajectories onto the road network. The graph representation is constructed based on the road segments in this directed graph. By utilizing Transformer sequence encoding, the trajectory representation is derived and hierarchical geographic encoding captures the GPS mapping of the original trajectories. Merging these two representations produces the final trajectory representation, serving as input for an LSTM-based variational autoencoder to reconstruct the trajectory representation, facilitating rapid online anomaly detection. Experimental findings on a large-scale taxi trajectory dataset illustrate the superior performance of GeoGNFTOD compared to baseline algorithms.
2
Yu, Xingtong, Zemin Liu, Yuan Fang et Xinming Zhang. « Learning to Count Isomorphisms with Graph Neural Networks ». Proceedings of the AAAI Conference on Artificial Intelligence 37, no 4 (26 juin 2023) : 4845–53. http://dx.doi.org/10.1609/aaai.v37i4.25610.
Texte intégralRésumé :
Subgraph isomorphism counting is an important problem on graphs, as many graph-based tasks exploit recurring subgraph patterns. Classical methods usually boil down to a backtracking framework that needs to navigate a huge search space with prohibitive computational cost. Some recent studies resort to graph neural networks (GNNs) to learn a low-dimensional representation for both the query and input graphs, in order to predict the number of subgraph isomorphisms on the input graph. However, typical GNNs employ a node-centric message passing scheme that receives and aggregates messages on nodes, which is inadequate in complex structure matching for isomorphism counting. Moreover, on an input graph, the space of possible query graphs is enormous, and different parts of the input graph will be triggered to match different queries. Thus, expecting a fixed representation of the input graph to match diversely structured query graphs is unrealistic. In this paper, we propose a novel GNN called Count-GNN for subgraph isomorphism counting, to deal with the above challenges. At the edge level, given that an edge is an atomic unit of encoding graph structures, we propose an edge-centric message passing scheme, where messages on edges are propagated and aggregated based on the edge adjacency to preserve fine-grained structural information. At the graph level, we modulate the input graph representation conditioned on the query, so that the input graph can be adapted to each query individually to improve their matching. Finally, we conduct extensive experiments on a number of benchmark datasets to demonstrate the superior performance of Count-GNN.
3
Bauer, Daniel. « Understanding Descriptions of Visual Scenes Using Graph Grammars ». Proceedings of the AAAI Conference on Artificial Intelligence 27, no 1 (29 juin 2013) : 1656–57. http://dx.doi.org/10.1609/aaai.v27i1.8498.
Texte intégralRésumé :
Automatic generation of 3D scenes from descriptions has applications in communication, education, and entertainment, but requires deep understanding of the input text. I propose thesis work on language understanding using graph-based meaning representations that can be decomposed into primitive spatial relations. The techniques used for analyzing text and transforming it into a scene representation are based on context-free graph grammars. The thesis develops methods for semantic parsing with graphs, acquisition of graph grammars, and satisfaction of spatial and world-knowledge constraints during parsing.
4
Wu, Xinyue, et Huilin Chen. « Augmented Feature Diffusion on Sparsely Sampled Subgraph ». Electronics 13, no 16 (15 août 2024) : 3249. http://dx.doi.org/10.3390/electronics13163249.
Texte intégralRésumé :
Link prediction is a fundamental problem in graphs. Currently, SubGraph Representation Learning (SGRL) methods provide state-of-the-art solutions for link prediction by transforming the task into a graph classification problem. However, existing SGRL solutions suffer from high computational costs and lack scalability. In this paper, we propose a novel SGRL framework called Augmented Feature Diffusion on Sparsely Sampled Subgraph (AFD3S). The AFD3S first uses a conditional variational autoencoder to augment the local features of the input graph, effectively improving the expressive ability of downstream Graph Neural Networks. Then, based on a random walk strategy, sparsely sampled subgraphs are obtained from the target node pairs, reducing computational and storage overhead. Graph diffusion is then performed on the sampled subgraph to achieve specific weighting. Finally, the diffusion matrix of the subgraph and its augmented feature matrix are used for feature diffusion to obtain operator-level node representations as inputs for the SGRL-based link prediction. Feature diffusion effectively simulates the message-passing process, simplifying subgraph representation learning, thus accelerating the training and inference speed of subgraph learning. Our proposed AFD3S achieves optimal prediction performance on several benchmark datasets, with significantly reduced storage and computational costs.
5
Cooray, Thilini, et Ngai-Man Cheung. « Graph-Wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning ». Proceedings of the AAAI Conference on Artificial Intelligence 36, no 6 (28 juin 2022) : 6420–28. http://dx.doi.org/10.1609/aaai.v36i6.20593.
Texte intégralRésumé :
Unsupervised graph-level representation learning plays a crucial role in a variety of tasks such as molecular property prediction and community analysis, especially when data annotation is expensive. Currently, most of the best-performing graph embedding methods are based on Infomax principle. The performance of these methods highly depends on the selection of negative samples and hurt the performance, if the samples were not carefully selected. Inter-graph similarity-based methods also suffer if the selected set of graphs for similarity matching is low in quality. To address this, we focus only on utilizing the current input graph for embedding learning. We are motivated by an observation from real-world graph generation processes where the graphs are formed based on one or more global factors which are common to all elements of the graph (e.g., topic of a discussion thread, solubility level of a molecule). We hypothesize extracting these common factors could be highly beneficial. Hence, this work proposes a new principle for unsupervised graph representation learning: Graph-wise Common latent Factor EXtraction (GCFX). We further propose a deep model for GCFX, deepGCFX, based on the idea of reversing the above-mentioned graph generation process which could explicitly extract common latent factors from an input graph and achieve improved results on downstream tasks to the current state-of-the-art. Through extensive experiments and analysis, we demonstrate that, while extracting common latent factors is beneficial for graph-level tasks to alleviate distractions caused by local variations of individual nodes or local neighbourhoods, it also benefits node-level tasks by enabling long-range node dependencies, especially for disassortative graphs.
6
Gildea, Daniel, Giorgio Satta et Xiaochang Peng. « Ordered Tree Decomposition for HRG Rule Extraction ». Computational Linguistics 45, no 2 (juin 2019) : 339–79. http://dx.doi.org/10.1162/coli_a_00350.
Texte intégralRésumé :
We present algorithms for extracting Hyperedge Replacement Grammar (HRG) rules from a graph along with a vertex order. Our algorithms are based on finding a tree decomposition of smallest width, relative to the vertex order, and then extracting one rule for each node in this structure. The assumption of a fixed order for the vertices of the input graph makes it possible to solve the problem in polynomial time, in contrast to the fact that the problem of finding optimal tree decompositions for a graph is NP-hard. We also present polynomial-time algorithms for parsing based on our HRGs, where the input is a vertex sequence and the output is a graph structure. The intended application of our algorithms is grammar extraction and parsing for semantic representation of natural language. We apply our algorithms to data annotated with Abstract Meaning Representations and report on the characteristics of the resulting grammars.
7
Miao, Fengyu, Xiuzhuang Zhou, Shungen Xiao et Shiliang Zhang. « A Graph Similarity Algorithm Based on Graph Partitioning and Attention Mechanism ». Electronics 13, no 19 (25 septembre 2024) : 3794. http://dx.doi.org/10.3390/electronics13193794.
Texte intégralRésumé :
In recent years, graph similarity algorithms have been extensively developed based on neural networks. However, with an increase in the node count in graphs, these models either suffer from a reduced representation ability or face a significant increase in the computational cost. To address this issue, a graph similarity algorithm based on graph partitioning and attention mechanisms was proposed in this study. Our method first divided each input graph into the subgraphs to directly extract the local structural features. The residual graph convolution and multihead self-attention mechanisms were employed to generate node embeddings for each subgraph, extract the feature information from the nodes, and regenerate the subgraph embeddings using varying attention weights. Initially, rough cosine similarity calculations were performed on all subgraph pairs from the two sets of subgraphs, with highly similar pairs selected for precise similarity computation. These results were then integrated into the similarity score for the input graph. The experimental results indicated that the proposed learning algorithm outperformed the traditional algorithms and similar computing models in terms of graph similarity computation performance.
8
Coşkun, Kemal Çağlar, Muhammad Hassan et Rolf Drechsler. « Equivalence Checking of System-Level and SPICE-Level Models of Linear Circuits ». Chips 1, no 1 (13 juin 2022) : 54–71. http://dx.doi.org/10.3390/chips1010006.
Texte intégralRésumé :
Due to the increasing complexity of analog circuits and their integration into System-on-Chips (SoC), the analog design and verification industry would greatly benefit from an expansion of system-level methodologies using SystemC AMS. These can provide a speed increase of over 100,000× in comparison to SPICE-level simulations and allow interoperability with digital tools at the system-level. However, a key barrier to the expansion of system-level tools for analog circuits is the lack of confidence in system-level models implemented in SystemC AMS. Functional equivalence of single Laplace Transfer Function (LTF) system-level models to respective SPICE-level models was successfully demonstrated recently. However, this is clearly not sufficient, as the complex systems comprise multiple LTF modules. In this article, we go beyond single LTF models, i.e., we develop a novel graph-based methodology to formally check equivalence between complex system-level and SPICE-level representations of Single-Input Single-Output (SISO) linear analog circuits, such as High-Pass Filters (HPF). To achieve this, first, we introduce a canonical representation in the form of a Signal-Flow Graph (SFG), which is used to functionally map the two representations from separate modeling levels. This canonical representation consists of the input and output nodes and a single edge between them with an LTF as its weight. Second, we create an SFG representation with linear graph modeling for SPICE-level models, whereas for system-level models we extract an SFG from the behavioral description. We then transform the SFG representations into the canonical representation by utilizing three graph manipulation techniques, namely node removal, parallel edge unification, and reflexive edge elimination. This allows us to establish functional equivalence between complex system-level models and SPICE-level models. We demonstrate the applicability of the proposed methodology by successfully applying it to complex circuits.
9
Zhang, Dong, Suzhong Wei, Shoushan Li, Hanqian Wu, Qiaoming Zhu et Guodong Zhou. « Multi-modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance ». Proceedings of the AAAI Conference on Artificial Intelligence 35, no 16 (18 mai 2021) : 14347–55. http://dx.doi.org/10.1609/aaai.v35i16.17687.
Texte intégralRésumé :
Multi-modal named entity recognition (MNER) aims to discover named entities in free text and classify them into pre-defined types with images. However, dominant MNER models do not fully exploit fine-grained semantic correspondences between semantic units of different modalities, which have the potential to refine multi-modal representation learning. To deal with this issue, we propose a unified multi-modal graph fusion (UMGF) approach for MNER. Specifically, we first represent the input sentence and image using a unified multi-modal graph, which captures various semantic relationships between multi-modal semantic units (words and visual objects). Then, we stack multiple graph-based multi-modal fusion layers that iteratively perform semantic interactions to learn node representations. Finally, we achieve an attention-based multi-modal representation for each word and perform entity labeling with a CRF decoder. Experimentation on the two benchmark datasets demonstrates the superiority of our MNER model.
10
Ren, Min, Yunlong Wang, Zhenan Sun et Tieniu Tan. « Dynamic Graph Representation for Occlusion Handling in Biometrics ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 07 (3 avril 2020) : 11940–47. http://dx.doi.org/10.1609/aaai.v34i07.6869.
Texte intégralRésumé :
The generalization ability of Convolutional neural networks (CNNs) for biometrics drops greatly due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrated the merits of both CNNs and graphical models to learn dynamic graph representations for occlusion problems in biometrics, called Dynamic Graph Representation (DGR). Convolutional features onto certain regions are re-crafted by a graph generator to establish the connections among the spatial parts of biometrics and build Feature Graphs based on these node representations. Each node of Feature Graphs corresponds to a specific part of the input image and the edges express the spatial relationships between parts. By analyzing the similarities between the nodes, the framework is able to adaptively remove the nodes representing the occluded parts. During dynamic graph matching, we propose a novel strategy to measure the distances of both nodes and adjacent matrixes. In this way, the proposed method is more convincing than CNNs-based methods because the dynamic graph method implies a more illustrative and reasonable inference of the biometrics decision. Experiments conducted on iris and face demonstrate the superiority of the proposed framework, which boosts the accuracy of occluded biometrics recognition by a large margin comparing with baseline methods.
11
Yin, Yongjing, Shaopeng Lai, Linfeng Song, Chulun Zhou, Xianpei Han, Junfeng Yao et Jinsong Su. « An External Knowledge Enhanced Graph-based Neural Network for Sentence Ordering ». Journal of Artificial Intelligence Research 70 (28 janvier 2021) : 545–66. http://dx.doi.org/10.1613/jair.1.12078.
Texte intégralRésumé :
As an important text coherence modeling task, sentence ordering aims to coherently organize a given set of unordered sentences. To achieve this goal, the most important step is to effectively capture and exploit global dependencies among these sentences. In this paper, we propose a novel and flexible external knowledge enhanced graph-based neural network for sentence ordering. Specifically, we first represent the input sentences as a graph, where various kinds of relations (i.e., entity-entity, sentence-sentence and entity-sentence) are exploited to make the graph representation more expressive and less noisy. Then, we introduce graph recurrent network to learn semantic representations of the sentences. To demonstrate the effectiveness of our model, we conduct experiments on several benchmark datasets. The experimental results and in-depth analysis show our model significantly outperforms the existing state-of-the-art models.
12
Malhi, Umar Subhan, Junfeng Zhou, Abdur Rasool et Shahbaz Siddeeq. « Efficient Visual-Aware Fashion Recommendation Using Compressed Node Features and Graph-Based Learning ». Machine Learning and Knowledge Extraction 6, no 3 (15 septembre 2024) : 2111–29. http://dx.doi.org/10.3390/make6030104.
Texte intégralRésumé :
In fashion e-commerce, predicting item compatibility using visual features remains a significant challenge. Current recommendation systems often struggle to incorporate high-dimensional visual data into graph-based learning models effectively. This limitation presents a substantial opportunity to enhance the precision and effectiveness of fashion recommendations. In this paper, we present the Visual-aware Graph Convolutional Network (VAGCN). This novel framework helps improve how visual features can be incorporated into graph-based learning systems for fashion item compatibility predictions. The VAGCN framework employs a deep-stacked autoencoder to convert the input image’s high-dimensional raw CNN visual features into more manageable low-dimensional representations. In addition to improving feature representation, the GCN can also reason more intelligently about predictions, which would not be possible without this compression. The GCN encoder processes nodes in the graph to capture structural and feature correlation. Following the GCN encoder, the refined embeddings are input to a multi-layer perceptron (MLP) to calculate compatibility scores. The approach extends to using neighborhood information only during the testing phase to help with training efficiency and generalizability in practical scenarios, a key characteristic of our model. By leveraging its ability to capture latent visual features and neighborhood-based learning, VAGCN thoroughly investigates item compatibility across various categories. This method significantly improves predictive accuracy, consistently outperforming existing benchmarks. These contributions tackle significant scalability and computational efficiency challenges, showcasing the potential transformation of recommendation systems through enhanced feature representation, paving the way for further innovations in the fashion domain.
13
Christensen, Andrew J., Ananya Sen Gupta et Ivars Kirsteins. « Graph representation learning on braid manifolds ». Journal of the Acoustical Society of America 152, no 4 (octobre 2022) : A39. http://dx.doi.org/10.1121/10.0015466.
Texte intégralRésumé :
The accuracy of autonomous sonar target recognition systems is usually hindered by morphing target features, unknown target geometry, and uncertainty caused by waveguide distortions to signal. Common “black-box” neural networks are not effective in addressing these challenges since they do not produce physically interpretable features. This work seeks to use recent advancements in machine learning to extract braid features that can be interpreted by a domain expert. We utilize Graph Neural Networks (GNNs) to discover braid manifolds in sonar ping spectra data. This approach represents the sonar ping data as a sequence of timestamped, sparse, dynamic graphs. These dynamic graph sequences are used as input into a GNN to produce feature dictionaries. GNNs ability to learn on complex systems of interactions help make them resilient to environmental uncertainty. To learn the evolving braid-like features of the sonar ping spectra graphs, a modified variation of Temporal Graph Networks (TGNs) is used. TGNs can perform prediction and classification tasks on timestamped dynamic graphs. The modified TGN in this work models the evolution of the sonar ping spectra graph to eventually perform graph-based classification. [Work supported by ONR grant N00014-21-1-2420.]
14
Ramezani, Majid, Mohammad-Reza Feizi-Derakhshi et Mohammad-Ali Balafar. « Knowledge Graph-Enabled Text-Based Automatic Personality Prediction ». Computational Intelligence and Neuroscience 2022 (20 juin 2022) : 1–18. http://dx.doi.org/10.1155/2022/3732351.
Texte intégralRésumé :
How people think, feel, and behave primarily is a representation of their personality characteristics. By being conscious of the personality characteristics of individuals whom we are dealing with or deciding to deal with, one can competently ameliorate the relationship, regardless of its type. With the rise of Internet-based communication infrastructures (social networks, forums, etc.), a considerable amount of human communications takes place there. The most prominent tool in such communications is the language in written and spoken form that adroitly encodes all those essential personality characteristics of individuals. Text-based Automatic Personality Prediction (APP) is the automated forecasting of the personality of individuals based on the generated/exchanged text contents. This paper presents a novel knowledge graph-enabled approach to text-based APP that relies on the Big Five personality traits. To this end, given a text, a knowledge graph, which is a set of interlinked descriptions of concepts, was built by matching the input text’s concepts with DBpedia knowledge base entries. Then, due to achieving a more powerful representation, the graph was enriched with the DBpedia ontology, NRC Emotion Intensity Lexicon, and MRC psycholinguistic database information. Afterwards, the knowledge graph, which is now a knowledgeable alternative for the input text, was embedded to yield an embedding matrix. Finally, to perform personality predictions, the resulting embedding matrix was fed to four suggested deep learning models independently, which are based on convolutional neural network (CNN), simple recurrent neural network (RNN), long short-term memory (LSTM), and bidirectional long short-term memory (BiLSTM). The results indicated considerable improvements in prediction accuracies in all of the suggested classifiers.
15
Xu, Jiarong, Yang Yang, Junru Chen, Xin Jiang, Chunping Wang, Jiangang Lu et Yizhou Sun. « Unsupervised Adversarially Robust Representation Learning on Graphs ». Proceedings of the AAAI Conference on Artificial Intelligence 36, no 4 (28 juin 2022) : 4290–98. http://dx.doi.org/10.1609/aaai.v36i4.20349.
Texte intégralRésumé :
Unsupervised/self-supervised pre-training methods for graph representation learning have recently attracted increasing research interests, and they are shown to be able to generalize to various downstream applications. Yet, the adversarial robustness of such pre-trained graph learning models remains largely unexplored. More importantly, most existing defense techniques designed for end-to-end graph representation learning methods require pre-specified label definitions, and thus cannot be directly applied to the pre-training methods. In this paper, we propose an unsupervised defense technique to robustify pre-trained deep graph models, so that the perturbations on the input graph can be successfully identified and blocked before the model is applied to different downstream tasks. Specifically, we introduce a mutual information-based measure, graph representation vulnerability (GRV), to quantify the robustness of graph encoders on the representation space. We then formulate an optimization problem to learn the graph representation by carefully balancing the trade-off between the expressive power and the robustness (i.e., GRV) of the graph encoder. The discrete nature of graph topology and the joint space of graph data make the optimization problem intractable to solve. To handle the above difficulty and to reduce computational expense, we further relax the problem and thus provide an approximate solution. Additionally, we explore a provable connection between the robustness of the unsupervised graph encoder and that of models on downstream tasks. Extensive experiments demonstrate that even without access to labels and tasks, our model is still able to enhance robustness against adversarial attacks on three downstream tasks (node classification, link prediction, and community detection) by an average of +16.5% compared with existing methods.
16
Lin, Mugang, Kunhui Wen, Xuanying Zhu, Huihuang Zhao et Xianfang Sun. « Graph Autoencoder with Preserving Node Attribute Similarity ». Entropy 25, no 4 (26 mars 2023) : 567. http://dx.doi.org/10.3390/e25040567.
Texte intégralRésumé :
The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the attribute information of nodes. Thus, the node attributes cannot be fully learned and the ability of the GAE to learn higher-quality representations is weakened. To address the issue, this paper proposes a novel GAE model that preserves node attribute similarity. The structural graph and the attribute neighbor graph, which is constructed based on the attribute similarity between nodes, are integrated as the encoder input using an effective fusion strategy. In the encoder, the attributes of the nodes can be aggregated both in their structural neighborhood and by their attribute similarity in their attribute neighborhood. This allows performing the fusion of the structural and node attribute information in the node representation by sharing the same encoder. In the decoder module, the adjacency matrix and the attribute similarity matrix of the nodes are reconstructed using dual decoders. The cross-entropy loss of the reconstructed adjacency matrix and the mean-squared error loss of the reconstructed node attribute similarity matrix are used to update the model parameters and ensure that the node representation preserves the original structural and node attribute similarity information. Extensive experiments on three citation networks show that the proposed method outperforms state-of-the-art algorithms in link prediction and node clustering tasks.
17
Kuropiatnyk, O. S., et B. M. Yakovenko. « Identification of the Program Text and Algorithm Correspondence Based on the Control Graph Constructive-Synthesizing Model ». Science and Transport Progress. Bulletin of Dnipropetrovsk National University of Railway Transport, no 4(94) (17 août 2021) : 12–24. http://dx.doi.org/10.15802/stp2021/245666.
Texte intégralRésumé :
Purpose.The main article purpose is to develop and implement the method for identifying the correspondence between the text and the program algorithm represented in the form of a flowchart. As part of the method work conversion of the input data in the graph representation is performed by means of constructive-synthesizing modelling. Methodology. To compare the program text and flowchart, we constructed a mathematical model for converting the program code into a graphical representation on the basis of control structures. To build the model, the apparatus of constructive-synthesizing modeling and its methods were used: specialization, concretization, interpretation and implementation. The graph representation of the text is created taking into account the control operators; the flowcharts are created using a json file containing the description of the diagram elements and their links. To compare the graphs we use the breadth-first search algorithm with the number of identical vertices being counted. To obtain the software implementation of the developed method and models we used the technology of object-oriented programming and CASE-technologies, which are based on the unified modeling language UML. Findings A method is proposed to present the text and the flowchart of the program in a uniform format of the directed graph (control graph) and to evaluate their correspondence by the number of identical vertices. For its formalization and automated usage, we developed constructive-synthesizing models of input data transformers. The program application was developed based on the models and the method. Originality. The methods of constructive-synthesizing modeling in the tasks of processing texts written in artificial languages were further developed. We developed the system of constructors, which transforms text program in C++ into a control graph. Practical value. The results are significant for solving such tasks as assembling program texts for borrowings detection, determining the correspondence of the program algorithms and their software implementations to improve coding skills. The graph representation produced by the developed system of constructors can be used for investigation of influence of optimization and code refactoring on the program complexity using McCabe's metrics.
18
Song, Zhiwei, Brittany Baur et Sushmita Roy. « Benchmarking graph representation learning algorithms for detecting modules in molecular networks ». F1000Research 12 (7 août 2023) : 941. http://dx.doi.org/10.12688/f1000research.134526.1.
Texte intégralRésumé :
Background: A common task in molecular network analysis is the detection of community structures or modules. Such modules are frequently associated with shared biological functions and are often disrupted in disease. Detection of community structure entails clustering nodes in the graph, and many algorithms apply a clustering algorithm on an input node embedding. Graph representation learning offers a powerful framework to learn node embeddings to perform various downstream tasks such as clustering. Deep embedding methods based on graph neural networks can have substantially better performance on machine learning tasks on graphs, including module detection; however, existing studies have focused on social and citation networks. It is currently unclear if deep embedding methods offer any advantage over shallow embedding methods for detecting modules in molecular networks. Methods: Here, we investigated deep and shallow graph representation learning algorithms on synthetic and real cell-type specific gene interaction networks to detect gene modules and identify pathways affected by sequence nucleotide polymorphisms. We used multiple criteria to assess the quality of the clusters based on connectivity as well as overrepresentation of biological processes. Results: On synthetic networks, deep embedding based on a variational graph autoencoder had superior performance as measured by modularity metrics, followed closely by shallow methods, node2vec and Graph Laplacian embedding. However, the performance of the deep methods worsens when the overall connectivity between clusters increases. On real molecular networks, deep embedding methods did not have a clear advantage and the performance depended upon the properties of the graph and the metrics. Conclusions: Deep graph representation learning algorithms for module detection-based tasks can be beneficial for some biological networks, but the performance depends upon the metrics and graph properties. Across different network types, Graph Laplacian embedding followed by node2vec are the best performing algorithms.
19
Sarfraz, Mubashar, Sheraz Alam, Sajjad A. Ghauri, Asad Mahmood, M. Nadeem Akram, M. Javvad Ur Rehman, M. Farhan Sohail et Teweldebrhan Mezgebo Kebedew. « Random Graph-Based M-QAM Classification for MIMO Systems ». Wireless Communications and Mobile Computing 2022 (15 avril 2022) : 1–10. http://dx.doi.org/10.1155/2022/9419764.
Texte intégralRésumé :
Automatic modulation classification (AMC) has been identified to perform a key role to realize technologies such as cognitive radio, dynamic spectrum management, and interference identification that are arguably pivotal to practical SG communication networks. Random graphs (RGs) have been used to better understand graph behavior and to tackle combinatorial challenges in general. In this research article, a novel modulation classifier is presented to recognize M-Quadrature Amplitude Modulation (QAM) signals using random graph theory. The proposed method demonstrates improved recognition rates for multiple-input multiple-output (MIMO) and single-input single-output (SISO) systems. The proposed method has the advantage of not requiring channel/signal to noise ratio estimate or timing/frequency offset correction. Undirected RGs are constructed based on features, which are extracted by taking sparse Fourier transform (SFT) of the received signal. This method is based on the graph representation of the SFT of the 2nd, 4th, and 8th power of the received signal. The simulation results are also compared to existing state-of-the-art methodologies, revealing that the suggested methodology is superior.
20
Zhang, Dehai, Anquan Ren, Jiashu Liang, Qing Liu, Haoxing Wang et Yu Ma. « Improving Medical X-ray Report Generation by Using Knowledge Graph ». Applied Sciences 12, no 21 (2 novembre 2022) : 11111. http://dx.doi.org/10.3390/app122111111.
Texte intégralRésumé :
In clinical diagnosis, radiological reports are essential to guide the patient’s treatment. However, writing radiology reports is a critical and time-consuming task for radiologists. Existing deep learning methods often ignore the interplay between medical findings, which may be a bottleneck limiting the quality of generated radiology reports. Our paper focuses on the automatic generation of medical reports from input chest X-ray images. In this work, we mine the associations between medical discoveries in the given texts and construct a knowledge graph based on the associations between medical discoveries. The patient’s chest X-ray image and clinical history file were used as input to extract the image–text hybrid features. Then, this feature is used as the input of the adjacency matrix of the knowledge graph, and the graph neural network is used to aggregate and transfer the information between each node to generate the situational representation of the disease with prior knowledge. These disease situational representations with prior knowledge are fed into the generator for self-supervised learning to generate radiology reports. We evaluate the performance of the proposed method using metrics from natural language generation and clinical efficacy on two public datasets. Our experiments show that our method outperforms state-of-the-art methods with the help of a knowledge graph constituted by prior knowledge of the patient.
21
Gao, Peng, et Hao Zhang. « Long-Term Loop Closure Detection through Visual-Spatial Information Preserving Multi-Order Graph Matching ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 06 (3 avril 2020) : 10369–76. http://dx.doi.org/10.1609/aaai.v34i06.6604.
Texte intégralRésumé :
Loop closure detection is a fundamental problem for simultaneous localization and mapping (SLAM) in robotics. Most of the previous methods only consider one type of information, based on either visual appearances or spatial relationships of landmarks. In this paper, we introduce a novel visual-spatial information preserving multi-order graph matching approach for long-term loop closure detection. Our approach constructs a graph representation of a place from an input image to integrate visual-spatial information, including visual appearances of the landmarks and the background environment, as well as the second and third-order spatial relationships between two and three landmarks, respectively. Furthermore, we introduce a new formulation that formulates loop closure detection as a multi-order graph matching problem to compute a similarity score directly from the graph representations of the query and template images, instead of performing conventional vector-based image matching. We evaluate the proposed multi-order graph matching approach based on two public long-term loop closure detection benchmark datasets, including the St. Lucia and CMU-VL datasets. Experimental results have shown that our approach is effective for long-term loop closure detection and it outperforms the previous state-of-the-art methods.
22
Hao, Yajie, Xing Chen, Ailu Fei, Qifeng Jia, Yu Chen, Jinsong Shao, Sanjeevi Pandiyan et Li Wang. « SG-ATT : A Sequence Graph Cross-Attention Representation Architecture for Molecular Property Prediction ». Molecules 29, no 2 (19 janvier 2024) : 492. http://dx.doi.org/10.3390/molecules29020492.
Texte intégralRésumé :
Existing formats based on the simplified molecular input line entry system (SMILES) encoding and molecular graph structure are designed to encode the complete semantic and structural information of molecules. However, the physicochemical properties of molecules are complex, and a single encoding of molecular features from SMILES sequences or molecular graph structures cannot adequately represent molecular information. Aiming to address this problem, this study proposes a sequence graph cross-attention (SG-ATT) representation architecture for a molecular property prediction model to efficiently use domain knowledge to enhance molecular graph feature encoding and combine the features of molecular SMILES sequences. The SG-ATT fuses the two-dimensional molecular features so that the current model input molecular information contains molecular structure information and semantic information. The SG-ATT was tested on nine molecular property prediction tasks. Among them, the biggest SG-ATT model performance improvement was 4.5% on the BACE dataset, and the average model performance improvement was 1.83% on the full dataset. Additionally, specific model interpretability studies were conducted to showcase the performance of the SG-ATT model on different datasets. In-depth analysis was provided through case studies of in vitro validation. Finally, network tools for molecular property prediction were developed for the use of researchers.
23
Bunke, H., et B. T. Messmer. « Recent Advances in Graph Matching ». International Journal of Pattern Recognition and Artificial Intelligence 11, no 01 (février 1997) : 169–203. http://dx.doi.org/10.1142/s0218001497000081.
Texte intégralRésumé :
A powerful and universal data structure with applications invarious subfields of science and engineering is graphs. In computer vision and image analysis, graphs are often used for the representation of structured objects. For example, if the problem is to recognize instances of known objects in an image, then often models, or prototypes, of the known objects are represented by means of graphs and stored in a database. The unknown objects in the input image are extracted by means of suitable preprocessing and segmentation algorithms, and represented by graphs that are analogous to the model graphs. Thus, the problem of object recognition is transformed into a graph matching problem. In this paper, it is assumed that there is an input graph that is given on-line, and a number of model, or prototype, graphs that are known a priori. We present a new approach to subgraph isomorphism detection which is based on a compact representation of the model graphs that is computed off-line. Subgraphs that appear multiple times within the same or within different model graphs are represented only once, thus reducing the computational effort to detect them in an input graph. In the extreme case where all model graphs are highly similar, the run time of the new algorithm becomes independent of the number of model graphs. We also describe an extension of this method to error-correcting graph matching. Furthermore, an approach to subgraph isomorphism detection based on decision trees is proposed. A decision tree is generated from the models in an off-line phase. This decision tree can be used for subgraph isomorphism detection. The time needed for decision tree traversal is only polynomial in terms of the number of nodes of the input graph. Moreover, the time complexity of the decision tree traversal is completely independent on the number of model graphs, regardless of their similarity. However, the size of the decision tree is exponential in the number of nodes of the models. To cut down the space complexity of the decision tree, some pruning strategies are discussed.
24
Tian, Luogeng, Bailong Yang, Xinli Yin, Kai Kang et Jing Wu. « Multipath Cross Graph Convolution for Knowledge Representation Learning ». Computational Intelligence and Neuroscience 2021 (28 décembre 2021) : 1–13. http://dx.doi.org/10.1155/2021/2547905.
Texte intégralRésumé :
In the past, most of the entity prediction methods based on embedding lacked the training of local core relationships, resulting in a deficiency in the end-to-end training. Aiming at this problem, we propose an end-to-end knowledge graph embedding representation method. It involves local graph convolution and global cross learning in this paper, which is called the TransC graph convolutional network (TransC-GCN). Firstly, multiple local semantic spaces are divided according to the largest neighbor. Secondly, a translation model is used to map the local entities and relationships into a cross vector, which serves as the input of GCN. Thirdly, through training and learning of local semantic relations, the best entities and strongest relations are found. The optimal entity relation combination ranking is obtained by evaluating the posterior loss function based on the mutual information entropy. Experiments show that this paper can obtain local entity feature information more accurately through the convolution operation of the lightweight convolutional neural network. Also, the maximum pooling operation helps to grasp the strong signal on the local feature, thereby avoiding the globally redundant feature. Compared with the mainstream triad prediction baseline model, the proposed algorithm can effectively reduce the computational complexity while achieving strong robustness. It also increases the inference accuracy of entities and relations by 8.1% and 4.4%, respectively. In short, this new method can not only effectively extract the local nodes and relationship features of the knowledge graph but also satisfy the requirements of multilayer penetration and relationship derivation of a knowledge graph.
25
Li, Linqing, et Zhifeng Wang. « Knowledge Graph-Enhanced Intelligent Tutoring System Based on Exercise Representativeness and Informativeness ». International Journal of Intelligent Systems 2023 (16 octobre 2023) : 1–19. http://dx.doi.org/10.1155/2023/2578286.
Texte intégralRésumé :
In the realm of online tutoring intelligent systems, e-learners are exposed to a substantial volume of learning content. The extraction and organization of exercises and skills hold significant importance in establishing clear learning objectives and providing appropriate exercise recommendations. Presently, knowledge graph-based recommendation algorithms have garnered considerable attention among researchers. However, these algorithms solely consider knowledge graphs with single relationships and do not effectively model exercise-rich features, such as exercise representativeness and informativeness. Consequently, this paper proposes a framework, namely, the Knowledge Graph Importance-Exercise Representativeness and Informativeness Framework, to address these two issues. The framework consists of four intricate components and a novel cognitive diagnosis model called the Neural Attentive Cognitive Diagnosis model to recommend the proper exercises. These components encompass the informativeness component, exercise representation component, knowledge importance component, and exercise representativeness component. The informativeness component evaluates the informational value of each exercise and identifies the candidate exercise set E C that exhibits the highest exercise informativeness. Moreover, the exercise representation component utilizes a graph neural network to process student records. The output of the graph neural network serves as the input for exercise-level attention and skill-level attention, ultimately generating exercise embeddings and skill embeddings. Furthermore, the skill embeddings are employed as input for the knowledge importance component. This component transforms a one-dimensional knowledge graph into a multidimensional one through four class relations and calculates skill importance weights based on novelty and popularity. Subsequently, the exercise representativeness component incorporates exercise weight knowledge coverage to select exercises from the candidate exercise set for the tested exercise set. Lastly, the cognitive diagnosis model leverages exercise representation and skill importance weights to predict student performance on the test set and estimate their knowledge state. To evaluate the effectiveness of our selection strategy, extensive experiments were conducted on two types of publicly available educational datasets. The experimental results demonstrate that our framework can recommend appropriate exercises to students, leading to improved student performance.
26
Xu, Jiakun, Bowen Xu, Gui-Song Xia, Liang Dong et Nan Xue. « Patched Line Segment Learning for Vector Road Mapping ». Proceedings of the AAAI Conference on Artificial Intelligence 38, no 6 (24 mars 2024) : 6288–96. http://dx.doi.org/10.1609/aaai.v38i6.28447.
Texte intégralRésumé :
This paper presents a novel approach to computing vector road maps from satellite remotely sensed images, building upon a well-defined Patched Line Segment (PaLiS) representation for road graphs that holds geometric significance. Unlike prevailing methods that derive road vector representations from satellite images using binary masks or keypoints, our method employs line segments. These segments not only convey road locations but also capture their orientations, making them a robust choice for representation. More precisely, given an input image, we divide it into non-overlapping patches and predict a suitable line segment within each patch. This strategy enables us to capture spatial and structural cues from these patch-based line segments, simplifying the process of constructing the road network graph without the necessity of additional neural networks for connectivity. In our experiments, we demonstrate how an effective representation of a road graph significantly enhances the performance of vector road mapping on established benchmarks, without requiring extensive modifications to the neural network architecture. Furthermore, our method achieves state-of-the-art performance with just 6 GPU hours of training, leading to a substantial 32-fold reduction in training costs in terms of GPU hours.
27
Yang, Liang, Chuan Wang, Junhua Gu, Xiaochun Cao et Bingxin Niu. « Why Do Attributes Propagate in Graph Convolutional Neural Networks ? » Proceedings of the AAAI Conference on Artificial Intelligence 35, no 5 (18 mai 2021) : 4590–98. http://dx.doi.org/10.1609/aaai.v35i5.16588.
Texte intégralRésumé :
Many efforts have been paid to enhance Graph Convolutional Network from the perspective of propagation under the philosophy that ``Propagation is the essence of the GCNNs". Unfortunately, its adverse effect is over-smoothing, which makes the performance dramatically drop. To prevent the over-smoothing, many variants are presented. However, the perspective of propagation can't provide an intuitive and unified interpretation to their effect on prevent over-smoothing. In this paper, we aim at providing a novel explanation to the question of "Why do attributes propagate in GCNNs?''. which not only gives the essence of the oversmoothing, but also illustrates why the GCN extensions, including multi-scale GCN and GCN with initial residual, can improve the performance. To this end, an intuitive Graph Representation Learning (GRL) framework is presented. GRL simply constrains the node representation similar with the original attribute, and encourages the connected nodes possess similar representations (pairwise constraint). Based on the proposed GRL, exiting GCN and its extensions can be proved as different numerical optimization algorithms, such as gradient descent, of our proposed GRL framework. Inspired by the superiority of conjugate gradient descent compared to common gradient descent, a novel Graph Conjugate Convolutional (GCC) network is presented to approximate the solution to GRL with fast convergence. Specifically, GCC adopts the obtained information of the last layer, which can be represented as the difference between the input and output of the last layer, as the input to the next layer. Extensive experiments demonstrate the superior performance of GCC.
28
Chuang, S. H. F., et M. R. Henderson. « Using Subgraph Isomorphisms to Recognize and Decompose Boundary Representation Features ». Journal of Mechanical Design 116, no 3 (1 septembre 1994) : 793–800. http://dx.doi.org/10.1115/1.2919452.
Texte intégralRésumé :
A method using subgraph isomorphisms is presented for both computer recognition of shape features and feature-based decomposition of a solid from a boundary representation (B-rep). Prior to the recognition process, the face-edge graph of an object is extracted from a B-rep and is labeled by shape elements as a shape graph, which is an abridged B-rep and is labeled by shape elements as a shape graph, which is an abridged B-rep input to the recognition system. A feature is defined by a user as a feature graph, which is conceptualized from a regional surface shape on a valid solid. Feature recognition is achieved by finding a subgraph from the shape graph of a designed object where the subgraph is isomorphic to a feature graph. Because of the high complexity in subgraph matching, a node classification algorithm is used to reduce the search space. Through this recognition process, the surface of a solid can be decomposed into a collection of features according to a library of feature graphs. The feature relationships are represented in a relationship graph considering the features as nodes and their relationships as arcs. This research shows that the definition of features can be user-definable and consist of valid boundary representation elements in the solid world, and that a heuristically fast algorithm can increase the possibility to recognize features in a reasonable time.
29
Sun, Guofei, Yongkang Wong, Mohan S. Kankanhalli, Xiangdong Li et Weidong Geng. « Enhanced 3D Shape Reconstruction With Knowledge Graph of Category Concept ». ACM Transactions on Multimedia Computing, Communications, and Applications 18, no 3 (31 août 2022) : 1–20. http://dx.doi.org/10.1145/3491224.
Texte intégralRésumé :
Reconstructing three-dimensional (3D) objects from images has attracted increasing attention due to its wide applications in computer vision and robotic tasks. Despite the promising progress of recent deep learning–based approaches, which directly reconstruct the full 3D shape without considering the conceptual knowledge of the object categories, existing models have limited usage and usually create unrealistic shapes. 3D objects have multiple forms of representation, such as 3D volume, conceptual knowledge, and so on. In this work, we show that the conceptual knowledge for a category of objects, which represents objects as prototype volumes and is structured by graph, can enhance the 3D reconstruction pipeline. We propose a novel multimodal framework that explicitly combines graph-based conceptual knowledge with deep neural networks for 3D shape reconstruction from a single RGB image. Our approach represents conceptual knowledge of a specific category as a structure-based knowledge graph. Specifically, conceptual knowledge acts as visual priors and spatial relationships to assist the 3D reconstruction framework to create realistic 3D shapes with enhanced details. Our 3D reconstruction framework takes an image as input. It first predicts the conceptual knowledge of the object in the image, then generates a 3D object based on the input image and the predicted conceptual knowledge. The generated 3D object satisfies the following requirements: (1) it is consistent with the predicted graph in concept, and (2) consistent with the input image in geometry. Extensive experiments on public datasets (i.e., ShapeNet, Pix3D, and Pascal3D+) with 13 object categories show that (1) our method outperforms the state-of-the-art methods, (2) our prototype volume-based conceptual knowledge representation is more effective, and (3) our pipeline-agnostic approach can enhance the reconstruction quality of various 3D shape reconstruction pipelines.
30
You, Peiting, Xiang Li, Fan Zhang et Quanzheng Li. « Connectivity-based Cortical Parcellation via Contrastive Learning on Spatial-Graph Convolution ». BME Frontiers 2022 (1 avril 2022) : 1–11. http://dx.doi.org/10.34133/2022/9814824.
Texte intégralRésumé :
Objective. Objective of this work is the development and evaluation of a cortical parcellation framework based on tractography-derived brain structural connectivity. Impact Statement. The proposed framework utilizes novel spatial-graph representation learning methods for solving the task of cortical parcellation, an important medical image analysis and neuroscientific problem. Introduction. The concept of “connectional fingerprint” has motivated many investigations on the connectivity-based cortical parcellation, especially with the technical advancement of diffusion imaging. Previous studies on multiple brain regions have been conducted with promising results. However, performance and applicability of these models are limited by the relatively simple computational scheme and the lack of effective representation of brain imaging data. Methods. We propose the Spatial-graph Convolution Parcellation (SGCP) framework, a two-stage deep learning-based modeling for the graph representation brain imaging. In the first stage, SGCP learns an effective embedding of the input data through a self-supervised contrastive learning scheme with the backbone encoder of a spatial-graph convolution network. In the second stage, SGCP learns a supervised classifier to perform voxel-wise classification for parcellating the desired brain region. Results. SGCP is evaluated on the parcellation task for 5 brain regions in a 15-subject DWI dataset. Performance comparisons between SGCP, traditional parcellation methods, and other deep learning-based methods show that SGCP can achieve superior performance in all the cases. Conclusion. Consistent good performance of the proposed SGCP framework indicates its potential to be used as a general solution for investigating the regional/subregional composition of human brain based on one or more connectivity measurements.
31
Oh, Dongsuk, Jungwoo Lim, Kinam Park et Heuiseok Lim. « Semantic Representation Using Sub-Symbolic Knowledge in Commonsense Reasoning ». Applied Sciences 12, no 18 (14 septembre 2022) : 9202. http://dx.doi.org/10.3390/app12189202.
Texte intégralRésumé :
The commonsense question and answering (CSQA) system predicts the right answer based on a comprehensive understanding of the question. Previous research has developed models that use QA pairs, the corresponding evidence, or the knowledge graph as an input. Each method executes QA tasks with representations of pre-trained language models. However, the ability of the pre-trained language model to comprehend completely remains debatable. In this study, adversarial attack experiments were conducted on question-understanding. We examined the restrictions on the question-reasoning process of the pre-trained language model, and then demonstrated the need for models to use the logical structure of abstract meaning representations (AMRs). Additionally, the experimental results demonstrated that the method performed best when the AMR graph was extended with ConceptNet. With this extension, our proposed method outperformed the baseline in diverse commonsense-reasoning QA tasks.
32
Ling, Shi Yong, et Jin Hong Gong. « Research of Composite Ontology Mapping Strategy on the Parsing Graph ». Advanced Materials Research 765-767 (septembre 2013) : 1068–72. http://dx.doi.org/10.4028/www.scientific.net/amr.765-767.1068.
Texte intégralRésumé :
According to complex context relation of ontology, considering different input schema, ontology graph is created with general environment. Based on ontology structure, the paper constructs multiple level graph representation, By introducing similarity propagation of structural and instance level on context relation and rapid mapping with a rapid matching algorithm, a composite ontology mapping strategy is proposed, which iteratively achieves ontology mapping result with reused idea. Finally feasibility and effectiveness of the strategy is proved by complexity analysis to algorithm and some contrast test.
33
Li, Dan, et Qian Gao. « Session Recommendation Model Based on Context-Aware and Gated Graph Neural Networks ». Computational Intelligence and Neuroscience 2021 (13 octobre 2021) : 1–10. http://dx.doi.org/10.1155/2021/7266960.
Texte intégralRésumé :
The graph neural network (GNN) based approach has been successfully applied to session-based recommendation tasks. However, in the face of complex and changing real-world situations, the existing session recommendation algorithms do not fully consider the context information in user decision-making; furthermore, the importance of context information for the behavior model has been widely recognized. Based on this, this paper presents a session recommendation model based on context-aware and gated graph neural networks (CA-GGNNs). First, this paper presents the session sequence as data of graph structure. Second, the embedding vector representation of each item in the session graph is obtained by using the gated graph neural network (GGNN). In this paper, the GRU in GGNN is expanded to replace the input matrix and the state matrix in the conventional GRU with input context captured in the session (e.g., time, location, and holiday) and interval context (representing the proportion of the total session time of each item in the session). Finally, a soft attention mechanism is used to capture users’ interests and preferences, and a recommendation list is given. The CA-GGNN model combines session sequence information with context information at each time. The results on the open Yoochoose and Diginetica datasets show that the model has significantly improved compared with the latest session recommendation methods.
34
Zou, Shuilong, Zhaoyang Liu, Kaiqi Wang, Jun Cao, Shixiong Liu, Wangping Xiong et Shaoyi Li. « A study on pharmaceutical text relationship extraction based on heterogeneous graph neural networks ». Mathematical Biosciences and Engineering 21, no 1 (2023) : 1489–507. http://dx.doi.org/10.3934/mbe.2024064.
Texte intégralRésumé :
<abstract> <p>Effective information extraction of pharmaceutical texts is of great significance for clinical research. The ancient Chinese medicine text has streamlined sentences and complex semantic relationships, and the textual relationships may exist between heterogeneous entities. The current mainstream relationship extraction model does not take into account the associations between entities and relationships when extracting, resulting in insufficient semantic information to form an effective structured representation. In this paper, we propose a heterogeneous graph neural network relationship extraction model adapted to traditional Chinese medicine (TCM) text. First, the given sentence and predefined relationships are embedded by bidirectional encoder representation from transformers (BERT fine-tuned) word embedding as model input. Second, a heterogeneous graph network is constructed to associate words, phrases, and relationship nodes to obtain the hidden layer representation. Then, in the decoding stage, two-stage subject-object entity identification method is adopted, and the identifier adopts a binary classifier to locate the start and end positions of the TCM entities, identifying all the subject-object entities in the sentence, and finally forming the TCM entity relationship group. Through the experiments on the TCM relationship extraction dataset, the results show that the precision value of the heterogeneous graph neural network embedded with BERT is 86.99% and the F1 value reaches 87.40%, which is improved by 8.83% and 10.21% compared with the relationship extraction models CNN, Bert-CNN, and Graph LSTM.</p> </abstract>
35
Fan, Zhiqiang, Fangyue Chen, Xiaokai Xia et Yu Liu. « EEG Emotion Classification Based on Graph Convolutional Network ». Applied Sciences 14, no 2 (15 janvier 2024) : 726. http://dx.doi.org/10.3390/app14020726.
Texte intégralRésumé :
EEG-based emotion recognition is a task that uses scalp-EEG data to classify the emotion states of humans. The study of EEG-based emotion recognition can contribute to a large spectrum of application fields including healthcare and human–computer interaction. Recent studies in neuroscience reveal that the brain regions and their interactions play an essential role in the processing of different stimuli and the generation of corresponding emotional states. Nevertheless, such regional interactions, which have been proven to be critical in recognizing emotions in neuroscience, are largely overlooked in existing machine learning or deep learning models, which focus on individual channels in brain signals. Motivated by this, in this paper, we present RGNet, a model that is designed to learn the regional level representation of EEG signal for accurate emotion recognition. Specifically, after applying preprocessing and feature extraction techniques on raw signals, RGNet adopts a novel region-wise encoder to extract the features of channels located within each region as input to compute the regional level features, enabling the model to effectively explore the regional functionality. A graph is then constructed by considering each region as a node and connections between regions as edges, upon which a graph convolutional network is designed with spectral filtering and learned adjacency matrix. Instead of focusing on only the spatial proximity, it allows the model to capture more complex functional relationships. We conducted experiments from the perspective of region division strategies, region encoders and input feature types. Our model has achieved 98.64% and 99.33% for Deap and Dreamer datasets, respectively. The comparison studies show that RGNet outperforms the majority of the existing models for emotion recognition from EEG signals.
36
Orlikowski, Cezary, et Rafał Hein. « Port-Based Modeling of Distributed-Lumped Parameter Systems ». Solid State Phenomena 164 (juin 2010) : 183–88. http://dx.doi.org/10.4028/www.scientific.net/ssp.164.183.
Texte intégralRésumé :
This paper presents a uniform, port-based approach for modeling of both lumped and distributed parameter systems. Port-based model of the distributed system has been defined by application of bond graph methodology and distributed transfer function method (DTFM). The proposed approach combines versatility of port-based modeling and accuracy of distributed transfer function method. A concise representation of lumped-distributed systems has been obtained. The proposed method of modeling enables to formulate input data for computer analysis by application of DTFM.
37
Chen, Zhen, Jia Huang, Shengzheng Liu et Haixia Long. « Multiscale Feature Fusion and Graph Convolutional Network for Detecting Ethereum Phishing Scams ». Electronics 13, no 6 (7 mars 2024) : 1012. http://dx.doi.org/10.3390/electronics13061012.
Texte intégralRésumé :
With the emergence of blockchain technology, the cryptocurrency market has experienced significant growth in recent years, simultaneously fostering environments conducive to cybercrimes such as phishing scams. Phishing scams on blockchain platforms like Ethereum have become a grave economic threat. Consequently, there is a pressing demand for effective detection mechanisms for these phishing activities to establish a secure financial transaction environment. However, existing methods typically utilize only the most recent transaction record when constructing features, resulting in the loss of vast amounts of transaction data and failing to adequately reflect the characteristics of nodes. Addressing this need, this study introduces a multiscale feature fusion approach integrated with a graph convolutional network model to detect phishing scams on Ethereum. A node basic feature set comprising 12 features is initially designed based on the Ethereum transaction dataset in the basic feature module. Subsequently, in the edge embedding representation module, all transaction times and amounts between two nodes are sorted, and a gate recurrent unit (GRU) neural network is employed to capture the temporal features within this transaction sequence, generating a fixed-length edge embedding representation from variable-length input. In the time trading feature module, attention weights are allocated to all embedding representations surrounding a node, aggregating the edge embedding representations and structural relationships into the node. Finally, combining basic and time trading features of the node, graph convolutional networks (GCNs), SAGEConv, and graph attention networks (GATs) are utilized to classify phishing nodes. The performance of these three graph convolution-based deep learning models is validated on a real Ethereum phishing scam dataset, demonstrating commendable efficiency. Among these, SAGEConv achieves an F1-score of 0.958, an AUC-ROC value of 0.956, and an AUC-PR value of 0.949, outperforming existing methods and baseline models.
38
Ryazanov, Yu D., et S. V. Nazina. « Building parsers based on syntax diagrams with multiport components ». Prikladnaya Diskretnaya Matematika, no 55 (2022) : 102–19. http://dx.doi.org/10.17223/20710410/55/8.
Texte intégralRésumé :
The problem of constructing parsers from syntax diagrams with multiport components (SD) is solved. An algorithm for constructing a parser based on the GLL algorithm is proposed, which results in the compact representation of the input chain parse forest. The proposed algorithm makes it possible to build parsers based on the SD of an arbitrary structure and does not require preliminary SD transformations. We introduce the concepts of “inference tree” and “parsing forest” for SD and describe the data structures used by the parser, such as a graph-structured stack, a parser descriptor, and a compact representation of the parsing forest. The algorithm for constructing parsers based on SD is described and an example of parser constructing is given.
39
Zou, Jun, Jing Wan, Hao Zhang et Yunbing Zhang. « A Multi-hop Path Query Answering Model for Knowledge Graph based on Neighborhood Aggregation and Transformer ». Journal of Physics : Conference Series 2560, no 1 (1 août 2023) : 012049. http://dx.doi.org/10.1088/1742-6596/2560/1/012049.
Texte intégralRésumé :
Abstract Multi-hop path query answering is a complex task in which a path needs to be inferred from a knowledge graph that contains a head entity and multi-hop relations. The objective is to identify the corresponding tail entity accurately. The representation of the path is a critical factor in this task. However, existing methods do not adequately consider the context information of the entities and relations in the path. To address this issue, this paper proposes a novel multi-hop path query answering model that utilizes an enhanced reasoning path feature representation to incorporate intermediate entity information and improve the accuracy of path query answering. The proposed model utilizes the neighborhood to aggregate the entity representation in the reasoning path. It employs a recurrent skipping network to splice the embedding of the relationship and the entity in the reasoning path based on their weight. Additionally, the model adds the position representation to obtain the reasoning path representation. Moreover, the model uses Bi-GRU and Transformer to obtain the local and global context features of each entity in the reasoning path. Finally, the reasoning path feature representation is input into the feedforward neural network and predicted through the softmax layer. The effectiveness of the proposed model in addressing the multi-hop path query answering task is demonstrated by experimental results on the WN18RR and FB15K-237 datasets. Specifically, the proposed model outperforms existing methods in terms of accuracy.
40
Yan, Zhaokun, Xiangquan Yang et Yu Jin. « Considerate motion imagination classification method using deep learning ». PLOS ONE 17, no 10 (20 octobre 2022) : e0276526. http://dx.doi.org/10.1371/journal.pone.0276526.
Texte intégralRésumé :
In order to improve the classification accuracy of motion imagination, a considerate motion imagination classification method using deep learning is proposed. Specifically, based on a graph structure suitable for electroencephalography as input, the proposed model can accurately represent the distribution of electroencephalography electrodes in non-Euclidean space and fully consider the spatial correlation between electrodes. In addition, the spatial-spectral-temporal multi-dimensional feature information was extracted from the spatial-temporal graph representation and spatial-spectral graph representation transformed from the original electroencephalography signal using the dual branch architecture. Finally, the attention mechanism and global feature aggregation module were designed and combined with graph convolution to adaptively capture the dynamic correlation intensity and effective feature of electroencephalography signals in various dimensions. A series of contrast experiments and ablation experiments on several different public brain-computer interface datasets demonstrated that the excellence of proposed method. It is worth mentioning that, the proposed model is a general framework for the classification of electroencephalography signals, which is suitable for emotion recognition, sleep staging and other fields based on electroencephalography research. Moreover, the model has the potential to be applied in the medical field of motion imagination rehabilitation in real life.
41
Wang, Baocheng, et Wentao Cai. « Attention-Enhanced Graph Neural Networks for Session-Based Recommendation ». Mathematics 8, no 9 (18 septembre 2020) : 1607. http://dx.doi.org/10.3390/math8091607.
Texte intégralRésumé :
Session-based recommendation, which aims to match user needs with rich resources based on anonymous sessions, nowadays plays a critical role in various online platforms (e.g., media streaming sites, search and e-commerce). Existing recommendation algorithms usually model a session as a sequence or a session graph to model transitions between items. Despite their effectiveness, we would argue that the performance of these methods is still flawed: (1) Using only fixed session item embedding without considering the diversity of users’ interests and target items. (2) For user’s long-term interest, the difficulty of capturing the different priorities for different items accurately. To tackle these defects, we propose a novel model which leverages both the target attentive network and self-attention network to improve the graph-neural-network (GNN)-based recommender. In our model, we first model user’s interaction sequences as session graphs which serves as the input of the GNN, and each node vector involved in session graph can be obtained via the GNN. Next, target attentive network can activates different user interests corresponding to varied target items (i.e., the session embedding learned varies with different target items), which can reveal the relevance between users’ interests and target items. At last, after applying the self-attention mechanism, the different priorities for different items can be captured to improve the precision of the long-term session representation. By using a hybrid of long-term and short-term session representation, we can capture users’ comprehensive interests at multiple levels. Extensive experiments demonstrate the effectiveness of our algorithm on two real-world datasets for session-based recommendation.
42
Hao, Yiran, Yiqiang Sheng et Jinlin Wang. « A Graph Representation Learning Algorithm for Low-Order Proximity Feature Extraction to Enhance Unsupervised IDS Preprocessing ». Applied Sciences 9, no 20 (22 octobre 2019) : 4473. http://dx.doi.org/10.3390/app9204473.
Texte intégralRésumé :
Most existing studies on an unsupervised intrusion detection system (IDS) preprocessing ignore the relationship among packets. According to the homophily hypothesis, the local proximity structure in the similarity relational graph has similar embedding after preprocessing. To improve the performance of IDS by building a relationship among packets, we propose a packet2vec learning algorithm that extracts accurate local proximity features based on graph representation by adding penalty to node2vec. In this algorithm, we construct a relational graph G’ by using each packet as a node, calculate the cosine similarity between packets as edges, and then explore the low-order proximity of each packet via the penalty-based random walk in G’. We use the above algorithm as a preprocessing method to enhance the accuracy of unsupervised IDS by retaining the local proximity features of packets maximally. The original features of the packet are combined with the local proximity features as the input of a deep auto-encoder for IDS. Experiments based on ISCX2012 show that the proposal outperforms the state-of-the-art algorithms by 11.6% with respect to the accuracy of unsupervised IDS. It is the first time to introduce graph representation learning for packet-embedded preprocessing in the field of IDS.
43
Fleischauer, Markus, et Sebastian Böcker. « BCD Beam Search : considering suboptimal partial solutions in Bad Clade Deletion supertrees ». PeerJ 6 (8 juin 2018) : e4987. http://dx.doi.org/10.7717/peerj.4987.
Texte intégralRésumé :
Supertree methods enable the reconstruction of large phylogenies. The supertree problem can be formalized in different ways in order to cope with contradictory information in the input. Some supertree methods are based on encoding the input trees in a matrix; other methods try to find minimum cuts in some graph. Recently, we introduced Bad Clade Deletion (BCD) supertrees which combines the graph-based computation of minimum cuts with optimizing a global objective function on the matrix representation of the input trees. The BCD supertree method has guaranteed polynomial running time and is very swift in practice. The quality of reconstructed supertrees was superior to matrix representation with parsimony (MRP) and usually on par with SuperFine for simulated data; but particularly for biological data, quality of BCD supertrees could not keep up with SuperFine supertrees. Here, we present a beam search extension for the BCD algorithm that keeps alive a constant number of partial solutions in each top-down iteration phase. The guaranteed worst-case running time of the new algorithm is still polynomial in the size of the input. We present an exact and a randomized subroutine to generate suboptimal partial solutions. Both beam search approaches consistently improve supertree quality on all evaluated datasets when keeping 25 suboptimal solutions alive. Supertree quality of the BCD Beam Search algorithm is on par with MRP and SuperFine even for biological data. This is the best performance of a polynomial-time supertree algorithm reported so far.
44
Kausar, Samina, et Andre O. Falcao. « Analysis and Comparison of Vector Space and Metric Space Representations in QSAR Modeling ». Molecules 24, no 9 (30 avril 2019) : 1698. http://dx.doi.org/10.3390/molecules24091698.
Texte intégralRésumé :
The performance of quantitative structure–activity relationship (QSAR) models largely depends on the relevance of the selected molecular representation used as input data matrices. This work presents a thorough comparative analysis of two main categories of molecular representations (vector space and metric space) for fitting robust machine learning models in QSAR problems. For the assessment of these methods, seven different molecular representations that included RDKit descriptors, five different fingerprints types (MACCS, PubChem, FP2-based, Atom Pair, and ECFP4), and a graph matching approach (non-contiguous atom matching structure similarity; NAMS) in both vector space and metric space, were subjected to state-of-art machine learning methods that included different dimensionality reduction methods (feature selection and linear dimensionality reduction). Five distinct QSAR data sets were used for direct assessment and analysis. Results show that, in general, metric-space and vector-space representations are able to produce equivalent models, but there are significant differences between individual approaches. The NAMS-based similarity approach consistently outperformed most fingerprint representations in model quality, closely followed by Atom Pair fingerprints. To further verify these findings, the metric space-based models were fitted to the same data sets with the closest neighbors removed. These latter results further strengthened the above conclusions. The metric space graph-based approach appeared significantly superior to the other representations, albeit at a significant computational cost.
45
Goldfarb, M., et N. Celanovic. « A Lumped Parameter Electromechanical Model for Describing the Nonlinear Behavior of Piezoelectric Actuators ». Journal of Dynamic Systems, Measurement, and Control 119, no 3 (1 septembre 1997) : 478–85. http://dx.doi.org/10.1115/1.2801282.
Texte intégralRésumé :
A lumped-parameter model of a piezoelectric stack actuator has been developed to describe actuator behavior for purposes of control system analysis and design, and in particular for control applications requiring accurate position tracking performance. In addition to describing the input-output dynamic behavior, the proposed model explains aspects of nonintuitive behavioral phenomena evinced by piezoelectric actuators, such as the input-output rate-independent hysteresis and the change in mechanical stiffness that results from altering electrical load. Bond graph terminology is incorporated to facilitate the energy-based formulation of the actuator model. The authors propose a new bond graph element, the generalized Maxwell resistive capacitor, as a lumped-parameter causal representation of rate-independent hysteresis. Model formulation is validated by comparing results of numerical simulations to experimental data.
46
Bahrami, Saeedeh, Alireza Bosaghzadeh et Fadi Dornaika. « Multi Similarity Metric Fusion in Graph-Based Semi-Supervised Learning ». Computation 7, no 1 (7 mars 2019) : 15. http://dx.doi.org/10.3390/computation7010015.
Texte intégralRésumé :
In semi-supervised label propagation (LP), the data manifold is approximated by a graph, which is considered as a similarity metric. Graph estimation is a crucial task, as it affects the further processes applied on the graph (e.g., LP, classification). As our knowledge of data is limited, a single approximation cannot easily find the appropriate graph, so in line with this, multiple graphs are constructed. Recently, multi-metric fusion techniques have been used to construct more accurate graphs which better represent the data manifold and, hence, improve the performance of LP. However, most of these algorithms disregard use of the information of label space in the LP process. In this article, we propose a new multi-metric graph-fusion method, based on the Flexible Manifold Embedding algorithm. Our proposed method represents a unified framework that merges two phases: graph fusion and LP. Based on one available view, different simple graphs were efficiently generated and used as input to our proposed fusion approach. Moreover, our method incorporated the label space information as a new form of graph, namely the Correlation Graph, with other similarity graphs. Furthermore, it updated the correlation graph to find a better representation of the data manifold. Our experimental results on four face datasets in face recognition demonstrated the superiority of the proposed method compared to other state-of-the-art algorithms.
47
Goto, Hiroyuki. « Model predictive control-based scheduler for repetitive discrete event systems with capacity constraints ». An International Journal of Optimization and Control : Theories & ; Applications (IJOCTA) 3, no 2 (29 mai 2013) : 73–83. http://dx.doi.org/10.11121/ijocta.01.2013.00140.
Texte intégralRésumé :
A model predictive control-based scheduler for a class of discrete event systems is designed and developed. We focus on repetitive, multiple-input, multiple-output, and directed acyclic graph structured systems on which capacity constraints can be imposed. The target system’s behaviour is described by linear equations in max-plus algebra, referred to as state-space representation. Assuming that the system’s performance can be improved by paying additional cost, we adjust the system parameters and determine control inputs for which the reference output signals can be observed. The main contribution of this research is twofold, 1: For systems with capacity constraints, we derived an output prediction equation as functions of adjustable variables in a recursive form, 2: Regarding the construct for the system’s representation, we improved the structure to accomplish general operations which are essential for adjusting the system parameters. The result of numerical simulation in a later section demonstrates the effectiveness of the developed controller.
48
Rashid, Pshtiwan Qader, et İlker Türker. « Lung Disease Detection Using U-Net Feature Extractor Cascaded by Graph Convolutional Network ». Diagnostics 14, no 12 (20 juin 2024) : 1313. http://dx.doi.org/10.3390/diagnostics14121313.
Texte intégralRésumé :
Computed tomography (CT) scans have recently emerged as a major technique for the fast diagnosis of lung diseases via image classification techniques. In this study, we propose a method for the diagnosis of COVID-19 disease with improved accuracy by utilizing graph convolutional networks (GCN) at various layer formations and kernel sizes to extract features from CT scan images. We apply a U-Net model to aid in segmentation and feature extraction. In contrast with previous research retrieving deep features from convolutional filters and pooling layers, which fail to fully consider the spatial connectivity of the nodes, we employ GCNs for classification and prediction to capture spatial connectivity patterns, which provides a significant association benefit. We handle the extracted deep features to form an adjacency matrix that contains a graph structure and pass it to a GCN along with the original image graph and the largest kernel graph. We combine these graphs to form one block of the graph input and then pass it through a GCN with an additional dropout layer to avoid overfitting. Our findings show that the suggested framework, called the feature-extracted graph convolutional network (FGCN), performs better in identifying lung diseases compared to recently proposed deep learning architectures that are not based on graph representations. The proposed model also outperforms a variety of transfer learning models commonly used for medical diagnosis tasks, highlighting the abstraction potential of the graph representation over traditional methods.
49
Tang, Chang, Xinwang Liu, Xinzhong Zhu, En Zhu, Zhigang Luo, Lizhe Wang et Wen Gao. « CGD : Multi-View Clustering via Cross-View Graph Diffusion ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 04 (3 avril 2020) : 5924–31. http://dx.doi.org/10.1609/aaai.v34i04.6052.
Texte intégralRésumé :
Graph based multi-view clustering has been paid great attention by exploring the neighborhood relationship among data points from multiple views. Though achieving great success in various applications, we observe that most of previous methods learn a consensus graph by building certain data representation models, which at least bears the following drawbacks. First, their clustering performance highly depends on the data representation capability of the model. Second, solving these resultant optimization models usually results in high computational complexity. Third, there are often some hyper-parameters in these models need to tune for obtaining the optimal results. In this work, we propose a general, effective and parameter-free method with convergence guarantee to learn a unified graph for multi-view data clustering via cross-view graph diffusion (CGD), which is the first attempt to employ diffusion process for multi-view clustering. The proposed CGD takes the traditional predefined graph matrices of different views as input, and learns an improved graph for each single view via an iterative cross diffusion process by 1) capturing the underlying manifold geometry structure of original data points, and 2) leveraging the complementary information among multiple graphs. The final unified graph used for clustering is obtained by averaging the improved view associated graphs. Extensive experiments on several benchmark datasets are conducted to demonstrate the effectiveness of the proposed method in terms of seven clustering evaluation metrics.
50
Liang, Shuang, Rong-Hua Li et George Baciu. « Cognitive Garment Panel Design Based on BSG Representation and Matching ». International Journal of Software Science and Computational Intelligence 4, no 1 (janvier 2012) : 84–99. http://dx.doi.org/10.4018/jssci.2012010104.
Texte intégralRésumé :
Previously, the fashion industry and apparel manufacturing have been applying intelligent CAD technologies with sketching interfaces to operate garment panel shapes in digital form. The authors propose a novel bi-segment graph (BSG) representation and matching approach to facilitate the searching of panel shapes for sketch-based cognitive garment design and recommendation. First in the front-tier, they provide a sketching interface for designers to input and edit the clothing panels. A panel shape is then decomposed into a sequence of connected segments and represented by the proposed BSG model to encode its intrinsic features. A new matching metric based on minimal spanning tree is also proposed to compute the similarity between two BSG models. The simulation of the resulting garment design is also visualized and returned to the user in 3D. Experiment results show the effectiveness and efficiency of the proposed method.