Journal articles on the topic 'Structural Graph Representations'
To see the other types of publications on this topic, follow the link: Structural Graph Representations.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Structural Graph Representations.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Zhou, Xiaojie, Pengjun Zhai, and Yu Fang. "Learning Description-Based Representations for Temporal Knowledge Graph Reasoning via Attentive CNN." Journal of Physics: Conference Series 2025, no. 1 (September 1, 2021): 012003. http://dx.doi.org/10.1088/1742-6596/2025/1/012003.
Full textAbstract:
Abstract Knowledge graphs have played a significant role in various applications and knowledge reasoning is one of the key tasks. However, the task gets more challenging when each fact is associated with a time annotation on temporal knowledge graph. Most of the existing temporal knowledge graph representation learning methods exploit structural information to learn the entity and relation representations. By these methods, those entities with similar structural information cannot be easily distinguished. Incorporating other information is an effective way to solve such problems. To address this problem, we propose a temporal knowledge graph representation learning method d-HyTE that incorporates entity descriptions. We learn structure-based representations of entities and relations and explore a deep convolutional neural network with attention to encode description-based representations of entities. The joint representation of two different representations of an entity is regarded as the final representation. We evaluate this method on link prediction and temporal scope prediction. Experimental results showed that our method d-HyTE outperformed the other baselines on many metrics.
2
Malaviya, Chaitanya, Chandra Bhagavatula, Antoine Bosselut, and Yejin Choi. "Commonsense Knowledge Base Completion with Structural and Semantic Context." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 03 (April 3, 2020): 2925–33. http://dx.doi.org/10.1609/aaai.v34i03.5684.
Full textAbstract:
Automatic KB completion for commonsense knowledge graphs (e.g., ATOMIC and ConceptNet) poses unique challenges compared to the much studied conventional knowledge bases (e.g., Freebase). Commonsense knowledge graphs use free-form text to represent nodes, resulting in orders of magnitude more nodes compared to conventional KBs ( ∼18x more nodes in ATOMIC compared to Freebase (FB15K-237)). Importantly, this implies significantly sparser graph structures — a major challenge for existing KB completion methods that assume densely connected graphs over a relatively smaller set of nodes.In this paper, we present novel KB completion models that can address these challenges by exploiting the structural and semantic context of nodes. Specifically, we investigate two key ideas: (1) learning from local graph structure, using graph convolutional networks and automatic graph densification and (2) transfer learning from pre-trained language models to knowledge graphs for enhanced contextual representation of knowledge. We describe our method to incorporate information from both these sources in a joint model and provide the first empirical results for KB completion on ATOMIC and evaluation with ranking metrics on ConceptNet. Our results demonstrate the effectiveness of language model representations in boosting link prediction performance and the advantages of learning from local graph structure (+1.5 points in MRR for ConceptNet) when training on subgraphs for computational efficiency. Further analysis on model predictions shines light on the types of commonsense knowledge that language models capture well.
3
Wang, Yifei, Shiyang Chen, Guobin Chen, Ethan Shurberg, Hang Liu, and Pengyu Hong. "Motif-Based Graph Representation Learning with Application to Chemical Molecules." Informatics 10, no. 1 (January 11, 2023): 8. http://dx.doi.org/10.3390/informatics10010008.
Full textAbstract:
This work considers the task of representation learning on the attributed relational graph (ARG). Both the nodes and edges in an ARG are associated with attributes/features allowing ARGs to encode rich structural information widely observed in real applications. Existing graph neural networks offer limited ability to capture complex interactions within local structural contexts, which hinders them from taking advantage of the expression power of ARGs. We propose motif convolution module (MCM), a new motif-based graph representation learning technique to better utilize local structural information. The ability to handle continuous edge and node features is one of MCM’s advantages over existing motif-based models. MCM builds a motif vocabulary in an unsupervised way and deploys a novel motif convolution operation to extract the local structural context of individual nodes, which is then used to learn higher level node representations via multilayer perceptron and/or message passing in graph neural networks. When compared with other graph learning approaches to classifying synthetic graphs, our approach is substantially better at capturing structural context. We also demonstrate the performance and explainability advantages of our approach by applying it to several molecular benchmarks.
4
Joaristi, Mikel, and Edoardo Serra. "SIR-GN: A Fast Structural Iterative Representation Learning Approach For Graph Nodes." ACM Transactions on Knowledge Discovery from Data 15, no. 6 (May 19, 2021): 1–39. http://dx.doi.org/10.1145/3450315.
Full textAbstract:
Graph representation learning methods have attracted an increasing amount of attention in recent years. These methods focus on learning a numerical representation of the nodes in a graph. Learning these representations is a powerful instrument for tasks such as graph mining, visualization, and hashing. They are of particular interest because they facilitate the direct use of standard machine learning models on graphs. Graph representation learning methods can be divided into two main categories: methods preserving the connectivity information of the nodes and methods preserving nodes’ structural information. Connectivity-based methods focus on encoding relationships between nodes, with connected nodes being closer together in the resulting latent space. While methods preserving structure generate a latent space where nodes serving a similar structural function in the network are encoded close to each other, independently of them being connected or even close to each other in the graph. While there are a lot of works that focus on preserving node connectivity, only a few works focus on preserving nodes’ structure. Properly encoding nodes’ structural information is fundamental for many real-world applications as it has been demonstrated that this information can be leveraged to successfully solve many tasks where connectivity-based methods usually fail. A typical example is the task of node classification, i.e., the assignment or prediction of a particular label for a node. Current limitations of structural representation methods are their scalability, representation meaning, and no formal proof that guaranteed the preservation of structural properties. We propose a new graph representation learning method, called Structural Iterative Representation learning approach for Graph Nodes ( SIR-GN ). In this work, we propose two variations ( SIR-GN: GMM and SIR-GN: K-Means ) and show how our best variation SIR-GN: K-Means : (1) theoretically guarantees the preservation of graph structural similarities, (2) provides a clear meaning about its representation and a way to interpret it with a specifically designed attribution procedure, and (3) is scalable and fast to compute. In addition, from our experiment, we show that SIR-GN: K-Means is often better or, in the worst-case comparable than the existing structural graph representation learning methods present in the literature. Also, we empirically show its superior scalability and computational performance when compared to other existing approaches.
5
Lyu, Gengyu, Xiang Deng, Yanan Wu, and Songhe Feng. "Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7647–54. http://dx.doi.org/10.1609/aaai.v36i7.20731.
Full textAbstract:
In multi-view multi-label learning (MVML), each instance is described by several heterogeneous feature representations and associated with multiple valid labels simultaneously. Although diverse MVML methods have been proposed over the last decade, most previous studies focus on leveraging the shared subspace across different views to represent the multi-view consensus information, while it is still an open issue whether such shared subspace representation is necessary when formulating the desired MVML model. In this paper, we propose a DeepGCN based View-Specific MVML method (D-VSM) which can bypass seeking for the shared subspace representation, and instead directly encoding the feature representation of each individual view through the deep GCN to couple with the information derived from the other views. Specifically, we first construct all instances under different feature representations into the corresponding feature graphs respectively, and then integrate them into a unified graph by integrating the different feature representations of each instance. Afterwards, the graph attention mechanism is adopted to aggregate and update all nodes on the unified graph to form structural representation for each instance, where both intra-view correlations and inter-view alignments have been jointly encoded to discover the underlying semantic relations. Finally, we derive a label confidence score for each instance by averaging the label confidence of its different feature representations with the multi-label soft margin loss. Extensive experiments have demonstrated that our proposed method significantly outperforms state-of-the-art methods.
6
Li, Wang, Siwei Wang, Xifeng Guo, Zhenyu Zhou, and En Zhu. "Auxiliary Graph for Attribute Graph Clustering." Entropy 24, no. 10 (October 2, 2022): 1409. http://dx.doi.org/10.3390/e24101409.
Full textAbstract:
Attribute graph clustering algorithms that include topological structural information into node characteristics for building robust representations have proven to have promising efficacy in a variety of applications. However, the presented topological structure emphasizes local links between linked nodes but fails to convey relationships between nodes that are not directly linked, limiting the potential for future clustering performance improvement. To solve this issue, we offer the Auxiliary Graph for Attribute Graph Clustering technique (AGAGC). Specifically, we construct an additional graph as a supervisor based on the node attribute. The additional graph can serve as an auxiliary supervisor that aids the present one. To generate a trustworthy auxiliary graph, we offer a noise-filtering approach. Under the supervision of both the pre-defined graph and an auxiliary graph, a more effective clustering model is trained. Additionally, the embeddings of multiple layers are merged to improve the discriminative power of representations. We offer a clustering module for a self-supervisor to make the learned representation more clustering-aware. Finally, our model is trained using a triplet loss. Experiments are done on four available benchmark datasets, and the findings demonstrate that the proposed model outperforms or is comparable to state-of-the-art graph clustering models.
7
Lv, Shangwen, Daya Guo, Jingjing Xu, Duyu Tang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, and Songlin Hu. "Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 8449–56. http://dx.doi.org/10.1609/aaai.v34i05.6364.
Full textAbstract:
Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on the evidence. Recent studies either learn to generate evidence from human-annotated evidence which is expensive to collect, or extract evidence from either structured or unstructured knowledge bases which fails to take advantages of both sources simultaneously. In this work, we propose to automatically extract evidence from heterogeneous knowledge sources, and answer questions based on the extracted evidence. Specifically, we extract evidence from both structured knowledge base (i.e. ConceptNet) and Wikipedia plain texts. We construct graphs for both sources to obtain the relational structures of evidence. Based on these graphs, we propose a graph-based approach consisting of a graph-based contextual word representation learning module and a graph-based inference module. The first module utilizes graph structural information to re-define the distance between words for learning better contextual word representations. The second module adopts graph convolutional network to encode neighbor information into the representations of nodes, and aggregates evidence with graph attention mechanism for predicting the final answer. Experimental results on CommonsenseQA dataset illustrate that our graph-based approach over both knowledge sources brings improvement over strong baselines. Our approach achieves the state-of-the-art accuracy (75.3%) on the CommonsenseQA dataset.
8
Ta'aseh, Nevo, and Offer Shai. "Network Graph Theory Perspective on Skeletal Structures for Theoretical and Educational Purposes." International Journal of Mechanical Engineering Education 36, no. 4 (October 2008): 294–319. http://dx.doi.org/10.7227/ijmee.36.4.3.
Full textAbstract:
The paper introduces an approach to the analysis of skeletal structures in which they are represented by a discrete mathematical model called graph representation. The paper shows that the reasoning upon the structure can be performed solely upon the representation, which, besides the theoretical value, presents a powerful educational tool. Students can learn skeletal structures entirely through the graph representations and derive advanced structural topics, including the conjugate theorem and the unit force method from the theorems and principles of network graph theory. The graph representations used in the paper for structures have also been applied to represent systems from different engineering disciplines. This provides students with a multidisciplinary perspective on analysis of engineering systems in general, and skeletal structures in particular.
9
Wang, Yu, Liang Hu, Yang Wu, and Wanfu Gao. "Graph Multihead Attention Pooling with Self-Supervised Learning." Entropy 24, no. 12 (November 29, 2022): 1745. http://dx.doi.org/10.3390/e24121745.
Full textAbstract:
Graph neural networks (GNNs), which work with graph-structured data, have attracted considerable attention and achieved promising performance on graph-related tasks. While the majority of existing GNN methods focus on the convolutional operation for encoding the node representations, the graph pooling operation, which maps the set of nodes into a coarsened graph, is crucial for graph-level tasks. We argue that a well-defined graph pooling operation should avoid the information loss of the local node features and global graph structure. In this paper, we propose a hierarchical graph pooling method based on the multihead attention mechanism, namely GMAPS, which compresses both node features and graph structure into the coarsened graph. Specifically, a multihead attention mechanism is adopted to arrange nodes into a coarsened graph based on their features and structural dependencies between nodes. In addition, to enhance the expressiveness of the cluster representations, a self-supervised mechanism is introduced to maximize the mutual information between the cluster representations and the global representation of the hierarchical graph. Our experimental results show that the proposed GMAPS obtains significant and consistent performance improvements compared with state-of-the-art baselines on six benchmarks from the biological and social domains of graph classification and reconstruction tasks.
10
Yoon, Jisung, Kai-Cheng Yang, Woo-Sung Jung, and Yong-Yeol Ahn. "Persona2vec: a flexible multi-role representations learning framework for graphs." PeerJ Computer Science 7 (March 30, 2021): e439. http://dx.doi.org/10.7717/peerj-cs.439.
Full textAbstract:
Graph embedding techniques, which learn low-dimensional representations of a graph, are achieving state-of-the-art performance in many graph mining tasks. Most existing embedding algorithms assign a single vector to each node, implicitly assuming that a single representation is enough to capture all characteristics of the node. However, across many domains, it is common to observe pervasively overlapping community structure, where most nodes belong to multiple communities, playing different roles depending on the contexts. Here, we propose persona2vec, a graph embedding framework that efficiently learns multiple representations of nodes based on their structural contexts. Using link prediction-based evaluation, we show that our framework is significantly faster than the existing state-of-the-art model while achieving better performance.
11
Faez, Faezeh, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah, and Hamid R. Rabiee. "SCGG: A deep structure-conditioned graph generative model." PLOS ONE 17, no. 11 (November 21, 2022): e0277887. http://dx.doi.org/10.1371/journal.pone.0277887.
Full textAbstract:
Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems. Making these methods able to consider different conditions during the generation procedure even increases their effectiveness by empowering them to generate new graph samples that meet the desired criteria. This paper presents a conditional deep graph generation method called SCGG that considers a particular type of structural conditions. Specifically, our proposed SCGG model takes an initial subgraph and autoregressively generates new nodes and their corresponding edges on top of the given conditioning substructure. The architecture of SCGG consists of a graph representation learning network and an autoregressive generative model, which is trained end-to-end. More precisely, the graph representation learning network is designed to compute continuous representations for each node in a graph, which are not only affected by the features of adjacent nodes, but also by the ones of farther nodes. This network is primarily responsible for providing the generation procedure with the structural condition, while the autoregressive generative model mainly maintains the generation history. Using this model, we can address graph completion, a rampant and inherently difficult problem of recovering missing nodes and their associated edges of partially observed graphs. The computational complexity of the SCGG method is shown to be linear in the number of graph nodes. Experimental results on both synthetic and real-world datasets demonstrate the superiority of our method compared with state-of-the-art baselines.
12
LEE, WAN-JUI, VERONIKA CHEPLYGINA, DAVID M. J. TAX, MARCO LOOG, and ROBERT P. W. DUIN. "BRIDGING STRUCTURE AND FEATURE REPRESENTATIONS IN GRAPH MATCHING." International Journal of Pattern Recognition and Artificial Intelligence 26, no. 05 (August 2012): 1260005. http://dx.doi.org/10.1142/s0218001412600051.
Full textAbstract:
Structures and features are opposite approaches in building representations for object recognition. Bridging the two is an essential problem in pattern recognition as the two opposite types of information are fundamentally different. As dissimilarities can be computed for both the dissimilarity representation can be used to combine the two. Attributed graphs contain structural as well as feature-based information. Neglecting the attributes yields a pure structural description. Isolating the features and neglecting the structure represents objects by a bag of features. In this paper we will show that weighted combinations of dissimilarities may perform better than these two extremes, indicating that these two types of information are essentially different and strengthen each other. In addition we present two more advanced integrations than weighted combining and show that these may improve the classification performances even further.
13
Fu, Sichao, Weifeng Liu, Weili Guan, Yicong Zhou, Dapeng Tao, and Changsheng Xu. "Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification." ACM Transactions on Multimedia Computing, Communications, and Applications 17, no. 1s (March 31, 2021): 1–13. http://dx.doi.org/10.1145/3412846.
Full textAbstract:
Over the past few years, graph representation learning (GRL) has received widespread attention on the feature representations of the non-Euclidean data. As a typical model of GRL, graph convolutional networks (GCN) fuse the graph Laplacian-based static sample structural information. GCN thus generalizes convolutional neural networks to acquire the sample representations with the variously high-order structures. However, most of existing GCN-based variants depend on the static data structural relationships. It will result in the extracted data features lacking of representativeness during the convolution process. To solve this problem, dynamic graph learning convolutional networks (DGLCN) on the application of semi-supervised classification are proposed. First, we introduce a definition of dynamic spectral graph convolution operation. It constantly optimizes the high-order structural relationships between data points according to the loss values of the loss function, and then fits the local geometry information of data exactly. After optimizing our proposed definition with the one-order Chebyshev polynomial, we can obtain a single-layer convolution rule of DGLCN. Due to the fusion of the optimized structural information in the learning process, multi-layer DGLCN can extract richer sample features to improve classification performance. Substantial experiments are conducted on citation network datasets to prove the effectiveness of DGLCN. Experiment results demonstrate that the proposed DGLCN obtains a superior classification performance compared to several existing semi-supervised classification models.
14
Zhang, Ruqing, Jiafeng Guo, Yixing Fan, Yanyan Lan, and Xueqi Cheng. "Structure Learning for Headline Generation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 9555–62. http://dx.doi.org/10.1609/aaai.v34i05.6501.
Full textAbstract:
Headline generation is an important problem in natural language processing, which aims to describe a document by a compact and informative headline. Some recent successes on this task have been achieved by advanced graph-based neural models, which marry the representational power of deep neural networks with the structural modeling ability of the relational sentence graphs. The advantages of graph-based neural models over traditional Seq2Seq models lie in that they can encode long-distance relationship between sentences beyond the surface linear structure. However, since documents are typically weakly-structured data, modern graph-based neural models usually rely on manually designed rules or some heuristics to construct the sentence graph a prior. This may largely limit the power and increase the cost of the graph-based methods. In this paper, therefore, we propose to incorporate structure learning into the graph-based neural models for headline generation. That is, we want to automatically learn the sentence graph using a data-driven way, so that we can unveil the document structure flexibly without prior heuristics or rules. To achieve this goal, we employ a deep & wide network to encode rich relational information between sentences for the sentence graph learning. For the deep component, we leverage neural matching models, either representation-focused or interaction-focused model, to learn semantic similarity between sentences. For the wide component, we encode a variety of discourse relations between sentences. A Graph Convolutional Network (GCN) is then applied over the sentence graph to generate high-level relational representations for headline generation. The whole model could be optimized end-to-end so that the structure and representation could be learned jointly. Empirical studies show that our model can significantly outperform the state-of-the-art headline generation models.
15
Xu, Chunlei, Batmend Horoldagva, and Lkhagva Buyantogtokh. "Cactus Graphs with Maximal Multiplicative Sum Zagreb Index." Symmetry 13, no. 5 (May 20, 2021): 913. http://dx.doi.org/10.3390/sym13050913.
Full textAbstract:
A connected graph G is said to be a cactus if any two cycles have at most one vertex in common. The multiplicative sum Zagreb index of a graph G is the product of the sum of the degrees of adjacent vertices in G. In this paper, we introduce several graph transformations that are useful tools for the study of the extremal properties of the multiplicative sum Zagreb index. Using these transformations and symmetric structural representations of some cactus graphs, we determine the graphs having maximal multiplicative sum Zagreb index for cactus graphs with the prescribed number of pendant vertices (cut edges). Furthermore, the graphs with maximal multiplicative sum Zagreb index are characterized among all cactus graphs of the given order.
16
BOURBAKIS, NIKOLAOS, and MICHAEL MILLS. "CONVERTING NATURAL LANGUAGE TEXT SENTENCES INTO SPN REPRESENTATIONS FOR ASSOCIATING EVENTS." International Journal of Semantic Computing 06, no. 03 (September 2012): 353–70. http://dx.doi.org/10.1142/s1793351x12500067.
Full textAbstract:
A better understanding of events many times requires the association and the efficient representation of multi-modal information. A good approach to this important issue is the development of a common platform for converting different modalities (such as images, text, etc.) into the same medium and associating them for efficient processing and understanding. In a previous paper we have presented a Local-Global graph model for the conversion of images into graphs with attributes and then into natural language (NL) text sentences [25]. Here, in this paper we propose the conversion of NL text sentences into graphs and then into Stochastic Petri-nets (SPN) descriptions in order to efficiently offer a model of associating "activities or changes" in multimodal information for events representation and understanding. The selection of the SPN graph model is due to its capability for efficiently representing structural and functional knowledge. Simple illustrative examples are provided for proving the concept proposed here.
17
Garcia-Hernandez, Carlos, Alberto Fernández, and Francesc Serratosa. "Learning the Edit Costs of Graph Edit Distance Applied to Ligand-Based Virtual Screening." Current Topics in Medicinal Chemistry 20, no. 18 (August 24, 2020): 1582–92. http://dx.doi.org/10.2174/1568026620666200603122000.
Full textAbstract:
Background: Graph edit distance is a methodology used to solve error-tolerant graph matching. This methodology estimates a distance between two graphs by determining the minimum number of modifications required to transform one graph into the other. These modifications, known as edit operations, have an edit cost associated that has to be determined depending on the problem. Objective: This study focuses on the use of optimization techniques in order to learn the edit costs used when comparing graphs by means of the graph edit distance. Methods: Graphs represent reduced structural representations of molecules using pharmacophore-type node descriptions to encode the relevant molecular properties. This reduction technique is known as extended reduced graphs. The screening and statistical tools available on the ligand-based virtual screening benchmarking platform and the RDKit were used. Results: In the experiments, the graph edit distance using learned costs performed better or equally good than using predefined costs. This is exemplified with six publicly available datasets: DUD-E, MUV, GLL&GDD, CAPST, NRLiSt BDB, and ULS-UDS. Conclusion: This study shows that the graph edit distance along with learned edit costs is useful to identify bioactivity similarities in a structurally diverse group of molecules. Furthermore, the target-specific edit costs might provide useful structure-activity information for future drug-design efforts.
18
Chapp, Dylan, Danny Rorabaugh, Kento Sato, Dong H. Ahn, and Michela Taufer. "A three-phase workflow for general and expressive representations of nondeterminism in HPC applications." International Journal of High Performance Computing Applications 33, no. 6 (August 20, 2019): 1175–84. http://dx.doi.org/10.1177/1094342019868826.
Full textAbstract:
Nondeterminism is an increasingly entrenched property of high-performance computing (HPC) applications and has recently been shown to seriously hamper debugging and reproducibility efforts. Tools for addressing the nondeterministic debugging problem have emerged, but they do not provide methods for systematically cataloging the nondeterminism in a given application. We propose a three-phase workflow for representing executions of nondeterministic message passing interface programs as event graphs, quantifying their structural similarity with graph kernels, and applying machine learning techniques to investigate shared properties across applications. We present an empirical study comparing two graph kernels’ suitability for this task and propose future uses of the methodology.
19
Sievers, Silvan, Gabriele Röger, Martin Wehrle, and Michael Katz. "Theoretical Foundations for Structural Symmetries of Lifted PDDL Tasks." Proceedings of the International Conference on Automated Planning and Scheduling 29 (May 25, 2021): 446–54. http://dx.doi.org/10.1609/icaps.v29i1.3509.
Full textAbstract:
We transfer the notion of structural symmetries to lifted planning task representations, based on abstract structures which we define to model planning tasks. We show that symmetries are preserved by common grounding methods and we shed some light on the relation to previous symmetry concepts used in planning. Using a suitable graph representation of lifted tasks, our experimental analysis of common planning benchmarks reveals that symmetries occur in the lifted representation of many domains. Our work establishes the theoretical ground for exploiting symmetries beyond their previous scope, such as for faster grounding and mutex generation, as well as for state space transformations and reductions.
20
Churkin, Alexander, Franziska Totzeck, Rami Zakh, Marina Parr, Tamir Tuller, Dmitrij Frishman, and Danny Barash. "A Mathematical Analysis of RNA Structural Motifs in Viruses." Mathematics 9, no. 6 (March 10, 2021): 585. http://dx.doi.org/10.3390/math9060585.
Full textAbstract:
RNA stem-loop structures play an important role in almost every step of the viral replication cycle. In this contribution, a mathematical analysis is performed on a large dataset of RNA secondary structure elements in the coding regions of viruses by using topological indices that capture the Laplacian eigenvalues of the associated RNA graph representations and thereby enable structural classification, supplemented by folding energy and mutational robustness. The application of such an analysis for viral RNA structural motifs is described, being able to extract structural categories such as stem-loop structures of different sizes according to the tree-graph representation of the RNA structure, in our attempt to find novel functional motifs. While the analysis is carried on a large dataset of viral RNA structures, it can be applied more generally to other data that involve RNA secondary structures in biological agents.
21
Vullo, Alessandro, and Paolo Frasconi. "Prediction of Protein Coarse Contact Maps." Journal of Bioinformatics and Computational Biology 01, no. 02 (July 2003): 411–31. http://dx.doi.org/10.1142/s0219720003000149.
Full textAbstract:
Prediction of topological representations of proteins that are geometrically invariants can contribute towards the solution of fundamental open problems in structural genomics like folding. In this paper we focus on coarse grained protein contact maps, a representation that describes the spatial neighborhood relation between secondary structure elements such as helices, beta sheets, and random coils. Our methodology is based on searching the graph space. The search algorithm is guided by an adaptive evaluation function computed by a specialized noncausal recursive connectionist architecture. The neural network is trained using candidate graphs generated during examples of successful searches. Our results demonstrate the viability of the approach for predicting coarse contact maps.
22
Prasad Raju Pathapati, V. V. N. R., and A. C. Rao. "A New Technique Based on Loops to Investigate Displacement Isomorphism in Planetary Gear Trains." Journal of Mechanical Design 124, no. 4 (November 26, 2002): 662–75. http://dx.doi.org/10.1115/1.1503373.
Full textAbstract:
The most important step in the structural synthesis of planetary gear trains (PGTs) requires the identification of isomorphism (rotational as well as displacement) between the graphs which represent the kinematic structure of planetary gear train. Previously used methods for identifying graph isomorphism yielded incorrect results. Literature review in this area shows there is inconsistency in results from six link, one degree-of-freedom onwards. The purpose of this paper is to present an efficient methodology through the use of Loop concept and Hamming number concept to detect displacement and rotational isomorphism in PGTs in an unambiguous way. New invariants for rotational graphs and displacement graphs called geared chain hamming strings and geared chain loop hamming strings are developed respectively to identify rotational and displacement isomorphism. This paper also presents a procedure to redraw conventional graph representation that not only clarifies the kinematic structure of a PGT but also averts the problem of pseudo isomorphism. Finally a thorough analysis of existing methods is carried out using the proposed technique and the results in the category of six links one degree-of-freedom are established and an Atlas comprises of graph representations in conventional form as well as in new form is presented.
23
Nadeem, Imran, Hani Shaker, Muhammad Hussain, and Asim Naseem. "Topological Indices of Para-line Graphs of V-Phenylenic Nanostructures." Open Mathematics 17, no. 1 (April 12, 2019): 260–66. http://dx.doi.org/10.1515/math-2019-0020.
Full textAbstract:
Abstract The degree-based topological indices are numerical graph invariants which are used to correlate the physical and chemical properties of a molecule with its structure. Para-line graphs are used to represent the structures of molecules in another way and these representations are important in structural chemistry. In this article, we study certain well-known degree-based topological indices for the para-line graphs of V-Phenylenic 2D lattice, V-Phenylenic nanotube and nanotorus by using the symmetries of their molecular graphs.
24
Yan, Hong-Sen, and Chin-Hsing Kuo. "REPRESENTATIONS AND IDENTIFICATIONS OF STRUCTURAL AND MOTION STATE CHARACTERISTICS OF MECHANISMS WITH VARIABLE TOPOLOGIES." Transactions of the Canadian Society for Mechanical Engineering 30, no. 1 (March 2006): 19–40. http://dx.doi.org/10.1139/tcsme-2006-0003.
Full textAbstract:
A mechanism that encounters a certain changes in its topological structure during operation is called a mechanism with variable topologies (MVT). This paper is developed for the structural and motion state representations and identifications of MVTs. For representing the topological structures of MVTs, a set of methods including graph and matrix representations is proposed. For representing the motion state characteristics of MVTs, the idea of finite-state machines is employed via the state tables and state graphs. And, two new concepts, the topological homomorphism and motion homomorphism, are proposed for the identifications of structural and motion state characteristics of MVTs. The results of this work provide a logical foundation for the topological analysis and synthesis of mechanisms with variable topologies.
25
Tang, Yaling, and Peng Yang. "Graph Enhanced Representation and Reasoning Model for Tabular Fact Verification." Journal of Physics: Conference Series 2303, no. 1 (July 1, 2022): 012030. http://dx.doi.org/10.1088/1742-6596/2303/1/012030.
Full textAbstract:
Abstract Tabular fact verification is a challenging task that requires obtaining relevant evidence from the table and utilizing them to verify a given claim. The main difficulty in tabular fact verification is that traditional language models cannot capture the underlying information carried in tabular data. To solve this problem, we propose GraERR, a Graph Enhanced Representation and Reasoning Model for Tabular Fact Verification. It consists of two modules: a data initial representation module based on the DeBERTa model and a graph-augmented representation and inference module. The former improves the inference ability of the model with a DeBERTa model pre-trained on the natural language inference dataset. The graph enhancement module enhances the model’s ability to learn table representations by effectively integrating textual and structural information in tables. The best results obtained experimentally on the InfoTabs dataset demonstrate the effectiveness of the GECMT model on the tabular fact verification task.
26
Hong, Huiting, Hantao Guo, Yucheng Lin, Xiaoqing Yang, Zang Li, and Jieping Ye. "An Attention-Based Graph Neural Network for Heterogeneous Structural Learning." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 4132–39. http://dx.doi.org/10.1609/aaai.v34i04.5833.
Full textAbstract:
In this paper, we focus on graph representation learning of heterogeneous information network (HIN), in which various types of vertices are connected by various types of relations. Most of the existing methods conducted on HIN revise homogeneous graph embedding models via meta-paths to learn low-dimensional vector space of HIN. In this paper, we propose a novel Heterogeneous Graph Structural Attention Neural Network (HetSANN) to directly encode structural information of HIN without meta-path and achieve more informative representations. With this method, domain experts will not be needed to design meta-path schemes and the heterogeneous information can be processed automatically by our proposed model. Specifically, we implicitly represent heterogeneous information using the following two methods: 1) we model the transformation between heterogeneous vertices through a projection in low-dimensional entity spaces; 2) afterwards, we apply the graph neural network to aggregate multi-relational information of projected neighborhood by means of attention mechanism. We also present three extensions of HetSANN, i.e., voices-sharing product attention for the pairwise relationships in HIN, cycle-consistency loss to retain the transformation between heterogeneous entity spaces, and multi-task learning with full use of information. The experiments conducted on three public datasets demonstrate that our proposed models achieve significant and consistent improvements compared to state-of-the-art solutions.
27
Jin, Yuan, Jiarui Lu, Runhan Shi, and Yang Yang. "EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction." Biomolecules 11, no. 12 (November 29, 2021): 1783. http://dx.doi.org/10.3390/biom11121783.
Full textAbstract:
The identification of drug-target interaction (DTI) plays a key role in drug discovery and development. Benefitting from large-scale drug databases and verified DTI relationships, a lot of machine-learning methods have been developed to predict DTIs. However, due to the difficulty in extracting useful information from molecules, the performance of these methods is limited by the representation of drugs and target proteins. This study proposes a new model called EmbedDTI to enhance the representation of both drugs and target proteins, and improve the performance of DTI prediction. For protein sequences, we leverage language modeling for pretraining the feature embeddings of amino acids and feed them to a convolutional neural network model for further representation learning. For drugs, we build two levels of graphs to represent compound structural information, namely the atom graph and substructure graph, and adopt graph convolutional network with an attention module to learn the embedding vectors for the graphs. We compare EmbedDTI with the existing DTI predictors on two benchmark datasets. The experimental results show that EmbedDTI outperforms the state-of-the-art models, and the attention module can identify the components crucial for DTIs in compounds.
28
Cheng, Pengyu, Yitong Li, Xinyuan Zhang, Liqun Chen, David Carlson, and Lawrence Carin. "Dynamic Embedding on Textual Networks via a Gaussian Process." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 7562–69. http://dx.doi.org/10.1609/aaai.v34i05.6255.
Full textAbstract:
Textual network embedding aims to learn low-dimensional representations of text-annotated nodes in a graph. Prior work in this area has typically focused on fixed graph structures; however, real-world networks are often dynamic. We address this challenge with a novel end-to-end node-embedding model, called Dynamic Embedding for Textual Networks with a Gaussian Process (DetGP). After training, DetGP can be applied efficiently to dynamic graphs without re-training or backpropagation. The learned representation of each node is a combination of textual and structural embeddings. Because the structure is allowed to be dynamic, our method uses the Gaussian process to take advantage of its non-parametric properties. To use both local and global graph structures, diffusion is used to model multiple hops between neighbors. The relative importance of global versus local structure for the embeddings is learned automatically. With the non-parametric nature of the Gaussian process, updating the embeddings for a changed graph structure requires only a forward pass through the learned model. Considering link prediction and node classification, experiments demonstrate the empirical effectiveness of our method compared to baseline approaches. We further show that DetGP can be straightforwardly and efficiently applied to dynamic textual networks.
29
Pandey, Mohit, Mariia Radaeva, Hazem Mslati, Olivia Garland, Michael Fernandez, Martin Ester, and Artem Cherkasov. "Ligand Binding Prediction Using Protein Structure Graphs and Residual Graph Attention Networks." Molecules 27, no. 16 (August 11, 2022): 5114. http://dx.doi.org/10.3390/molecules27165114.
Full textAbstract:
Computational prediction of ligand–target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures. Herein, we present the development of the PSG-BAR (Protein Structure Graph-Binding Affinity Regression) approach that utilizes 3D structural information of the proteins along with 2D graph representations of ligands. The method also introduces attention scores to selectively weight protein regions that are most important for ligand binding. Results: The developed approach demonstrates the state-of-the-art performance on several binding affinity benchmarking datasets. The attention-based pooling of protein graphs enables identification of surface residues as critical residues for protein–ligand binding. Finally, we validate our model predictions against an experimental assay on a viral main protease (Mpro)—the hallmark target of SARS-CoV-2 coronavirus.
30
Frisoni, Giacomo, Gianluca Moro, Giulio Carlassare, and Antonella Carbonaro. "Unsupervised Event Graph Representation and Similarity Learning on Biomedical Literature." Sensors 22, no. 1 (December 21, 2021): 3. http://dx.doi.org/10.3390/s22010003.
Full textAbstract:
The automatic extraction of biomedical events from the scientific literature has drawn keen interest in the last several years, recognizing complex and semantically rich graphical interactions otherwise buried in texts. However, very few works revolve around learning embeddings or similarity metrics for event graphs. This gap leaves biological relations unlinked and prevents the application of machine learning techniques to promote discoveries. Taking advantage of recent deep graph kernel solutions and pre-trained language models, we propose Deep Divergence Event Graph Kernels (DDEGK), an unsupervised inductive method to map events into low-dimensional vectors, preserving their structural and semantic similarities. Unlike most other systems, DDEGK operates at a graph level and does not require task-specific labels, feature engineering, or known correspondences between nodes. To this end, our solution compares events against a small set of anchor ones, trains cross-graph attention networks for drawing pairwise alignments (bolstering interpretability), and employs transformer-based models to encode continuous attributes. Extensive experiments have been done on nine biomedical datasets. We show that our learned event representations can be effectively employed in tasks such as graph classification, clustering, and visualization, also facilitating downstream semantic textual similarity. Empirical results demonstrate that DDEGK significantly outperforms other state-of-the-art methods.
31
Pratsiovytyi, M., V. Drozdenko, I. Lysenko, and Yu Maslova. "INVERSOR OF DIGITS OF TWO-BASE G–REPRESENTATION OF REAL NUMBERS AND ITS STRUCTURAL FRACTALITY." Bukovinian Mathematical Journal 10, no. 1 (2022): 100–109. http://dx.doi.org/10.31861/bmj2022.01.09.
Full textAbstract:
In the paper, we introduce a new two-symbol system of representation for numbers from segment $[0;0,5]$ with alphabet (set of digits) $A=\{0;1\}$ and two bases 2 and $-2$: \[x=\dfrac{\alpha_1}{2}+\dfrac{1}{2}\sum\limits^\infty_{k=1}\dfrac{\alpha_{k+1}}{2^{k-(\alpha_1+\ldots+\alpha_k)}(-2)^{\alpha_1+\ldots+\alpha_k}}\equiv \Delta^{G}_{\alpha_1\alpha_2\ldots\alpha_k\ldots}, \;\;\; \alpha_k\in \{0;1\}.\] We compare this new system with classic binary system. The function $I(x=\Delta^G_{\alpha_1\ldots \alpha_n\ldots})=\Delta^G_{1-\alpha_1,\ldots, 1-\alpha_n\ldots}$, such that digits of its $G$--representation are inverse (opposite) to digits of $G$--representation of argument is considered in detail. This function is well-defined at points having two $G$--representations provided we use only one of them. We prove that inversor is a function of unbounded variation, continuous function at points having a unique $G$--representation, and right- or left-continuous at points with two representations. The values of all jumps of the function are calculated. We prove also that the function does not have monotonicity intervals and its graph has a self-similar structure.
32
Ng, J. C. F., and F. Fraternali. "Understanding the structural details of APOBEC3-DNA interactions using graph-based representations." Current Research in Structural Biology 2 (2020): 130–43. http://dx.doi.org/10.1016/j.crstbi.2020.07.001.
Full text
33
Bin, Chenzhong, Saige Qin, Guanjun Rao, Tianlong Gu, and Liang Chang. "Multiview Translation Learning for Knowledge Graph Embedding." Scientific Programming 2020 (August 25, 2020): 1–9. http://dx.doi.org/10.1155/2020/7084958.
Full textAbstract:
Recently, knowledge graph embedding methods have attracted numerous researchers’ interest due to their outstanding effectiveness and robustness in knowledge representation. However, there are still some limitations in the existing methods. On the one hand, translation-based representation models focus on conceiving translation principles to represent knowledge from a global perspective, while they fail to learn various types of relational facts discriminatively. It is prone to make the entity congestion of complex relational facts in the embedding space reducing the precision of representation vectors associating with entities. On the other hand, parallel subgraphs extracted from the original graph are used to learn local relational facts discriminatively. However, it probably causes the relational fact damage of the original knowledge graph to some degree during the subgraph extraction. Thus, previous methods are unable to learn local and global knowledge representation uniformly. To that end, we propose a multiview translation learning model, named MvTransE, which learns relational facts from global-view and local-view perspectives, respectively. Specifically, we first construct multiple parallel subgraphs from an original knowledge graph by considering entity semantic and structural features simultaneously. Then, we embed the original graph and construct subgraphs into the corresponding global and local feature spaces. Finally, we propose a multiview fusion strategy to integrate multiview representations of relational facts. Extensive experiments on four public datasets demonstrate the superiority of our model in knowledge graph representation tasks compared to state-of-the-art methods.
34
Rica, Elena, Susana Álvarez, and Francesc Serratosa. "Ligand-Based Virtual Screening Based on the Graph Edit Distance." International Journal of Molecular Sciences 22, no. 23 (November 25, 2021): 12751. http://dx.doi.org/10.3390/ijms222312751.
Full textAbstract:
Chemical compounds can be represented as attributed graphs. An attributed graph is a mathematical model of an object composed of two types of representations: nodes and edges. Nodes are individual components, and edges are relations between these components. In this case, pharmacophore-type node descriptions are represented by nodes and chemical bounds by edges. If we want to obtain the bioactivity dissimilarity between two chemical compounds, a distance between attributed graphs can be used. The Graph Edit Distance allows computing this distance, and it is defined as the cost of transforming one graph into another. Nevertheless, to define this dissimilarity, the transformation cost must be properly tuned. The aim of this paper is to analyse the structural-based screening methods to verify the quality of the Harper transformation costs proposal and to present an algorithm to learn these transformation costs such that the bioactivity dissimilarity is properly defined in a ligand-based virtual screening application. The goodness of the dissimilarity is represented by the classification accuracy. Six publicly available datasets—CAPST, DUD-E, GLL&GDD, NRLiSt-BDB, MUV and ULS-UDS—have been used to validate our methodology and show that with our learned costs, we obtain the highest ratios in identifying the bioactivity similarity in a structurally diverse group of molecules.
35
Bielecki, Andrzej, and Piotr Śmigielski. "Three-Dimensional Outdoor Analysis of Single Synthetic Building Structures by an Unmanned Flying Agent Using Monocular Vision." Sensors 21, no. 21 (November 1, 2021): 7270. http://dx.doi.org/10.3390/s21217270.
Full textAbstract:
An algorithm designed for analysis and understanding a 3D urban-type environment by an autonomous flying agent, equipped only with a monocular vision, is presented. The algorithm is hierarchical and is based on the structural representation of the analyzed scene. Firstly, the robot observes the scene from a high altitude to build a 2D representation of a single object and a graph representation of the 2D scene. The 3D representation of each object arises as a consequence of the robot’s actions, as a result of which it projects the object’s solid on different planes. The robot assigns the obtained representations to the corresponding vertex of the created graph. The algorithm was tested by using the embodied robot operating on the real scene. The tests showed that the robot equipped with the algorithm was able not only to localize the predefined object, but also to perform safe, collision-free maneuvers close to the structures in the scene.
36
Mu, Shanlei, Yaliang Li, Wayne Xin Zhao, Siqing Li, and Ji-Rong Wen. "Knowledge-Guided Disentangled Representation Learning for Recommender Systems." ACM Transactions on Information Systems 40, no. 1 (January 31, 2022): 1–26. http://dx.doi.org/10.1145/3464304.
Full textAbstract:
In recommender systems, it is essential to understand the underlying factors that affect user-item interaction. Recently, several studies have utilized disentangled representation learning to discover such hidden factors from user-item interaction data, which shows promising results. However, without any external guidance signal, the learned disentangled representations lack clear meanings, and are easy to suffer from the data sparsity issue. In light of these challenges, we study how to leverage knowledge graph (KG) to guide the disentangled representation learning in recommender systems. The purpose for incorporating KG is twofold, making the disentangled representations interpretable and resolving data sparsity issue. However, it is not straightforward to incorporate KG for improving disentangled representations, because KG has very different data characteristics compared with user-item interactions. We propose a novel K nowledge-guided D isentangled R epresentations approach ( KDR ) to utilizing KG to guide the disentangled representation learning in recommender systems. The basic idea, is to first learn more interpretable disentangled dimensions (explicit disentangled representations) based on structural KG, and then align implicit disentangled representations learned from user-item interaction with the explicit disentangled representations. We design a novel alignment strategy based on mutual information maximization. It enables the KG information to guide the implicit disentangled representation learning, and such learned disentangled representations will correspond to semantic information derived from KG. Finally, the fused disentangled representations are optimized to improve the recommendation performance. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed model in terms of both performance and interpretability.
37
Greco, Gianluigi, and Francesco Scarcello. "On the power of structural decompositions of graph-based representations of constraint problems." Artificial Intelligence 174, no. 5-6 (April 2010): 382–409. http://dx.doi.org/10.1016/j.artint.2009.12.004.
Full text
38
Pan, Zhiqiang, Wanyu Chen, and Honghui Chen. "Dynamic Graph Learning for Session-Based Recommendation." Mathematics 9, no. 12 (June 19, 2021): 1420. http://dx.doi.org/10.3390/math9121420.
Full textAbstract:
Session-based recommendation (SBRS) aims to make recommendations for users merely based on the ongoing session. Existing GNN-based methods achieve satisfactory performance by exploiting the pair-wise item transition pattern; however, they ignore the temporal evolution of the session graphs over different time-steps. Moreover, the widely applied cross-entropy loss with softmax in SBRS faces the serious overfitting problem. To deal with the above issues, we propose dynamic graph learning for session-based recommendation (DGL-SR). Specifically, we design a dynamic graph neural network (DGNN) to simultaneously take the graph structural information and the temporal dynamics into consideration for learning the dynamic item representations. Moreover, we propose a corrective margin softmax (CMS) to prevent overfitting in the model optimization by correcting the gradient of the negative samples. Comprehensive experiments are conducted on two benchmark datasets, that is, Diginetica and Gowalla, and the experimental results show the superiority of DGL-SR over the state-of-the-art baselines in terms of Recall@20 and MRR@20, especially on hitting the target item in the recommendation list.
39
Liu, Fangyu, Muhao Chen, Dan Roth, and Nigel Collier. "Visual Pivoting for (Unsupervised) Entity Alignment." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 5 (May 18, 2021): 4257–66. http://dx.doi.org/10.1609/aaai.v35i5.16550.
Full textAbstract:
This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs). Images are natural components of many existing KGs. By combining visual knowledge with other auxiliary information, we show that the proposed new approach, EVA, creates a holistic entity representation that provides strong signals for cross-graph entity alignment. Besides, previous entity alignment methods require human labelled seed alignment, restricting availability. EVA provides a completely unsupervised solution by leveraging the visual similarity of entities to create an initial seed dictionary (visual pivots). Experiments on benchmark data sets DBP15k and DWY15k show that EVA offers state-of-the-art performance on both monolingual and cross-lingual entity alignment tasks. Furthermore, we discover that images are particularly useful to align long-tail KG entities, which inherently lack the structural contexts necessary for capturing the correspondences. Code release: https://github.com/cambridgeltl/eva; project page: http://cogcomp.org/page/publication view/927.
40
Li, Zejun, Zhongyu Wei, Zhihao Fan, Haijun Shan, and Xuanjing Huang. "An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-level Structural Information." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 15 (May 18, 2021): 13324–32. http://dx.doi.org/10.1609/aaai.v35i15.17573.
Full textAbstract:
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach achieves positive results, it introduces a sampling bias and fails to distinguish instances with high semantic similarity. To alleviate the bias, we propose a new sampling strategy to select additional intra-document image-sentence pairs as positive or negative samples. Furthermore, to recognize the complex pattern in intra-document samples, we propose a Transformer based model to capture fine-grained features and implicitly construct a graph for each document, where concepts in a document are introduced to bridge the representation learning of images and sentences in the context of a document. Experimental results show the effectiveness of our approach to alleviate the bias and learn well-aligned multimodal representations.
41
Yan, Zichao, William L. Hamilton, and Mathieu Blanchette. "Graph neural representational learning of RNA secondary structures for predicting RNA-protein interactions." Bioinformatics 36, Supplement_1 (July 1, 2020): i276—i284. http://dx.doi.org/10.1093/bioinformatics/btaa456.
Full textAbstract:
Abstract Motivation RNA-protein interactions are key effectors of post-transcriptional regulation. Significant experimental and bioinformatics efforts have been expended on characterizing protein binding mechanisms on the molecular level, and on highlighting the sequence and structural traits of RNA that impact the binding specificity for different proteins. Yet our ability to predict these interactions in silico remains relatively poor. Results In this study, we introduce RPI-Net, a graph neural network approach for RNA-protein interaction prediction. RPI-Net learns and exploits a graph representation of RNA molecules, yielding significant performance gains over existing state-of-the-art approaches. We also introduce an approach to rectify an important type of sequence bias caused by the RNase T1 enzyme used in many CLIP-Seq experiments, and we show that correcting this bias is essential in order to learn meaningful predictors and properly evaluate their accuracy. Finally, we provide new approaches to interpret the trained models and extract simple, biologically interpretable representations of the learned sequence and structural motifs. Availability and implementation Source code can be accessed at https://www.github.com/HarveyYan/RNAonGraph. Supplementary information Supplementary data are available at Bioinformatics online.
42
Huang, Shih-Ying, and Kamal Youcef-Toumi. "Explicit Energy Storage Fields and Their Application to Structural Property Inspection of Physical Systems." Journal of Dynamic Systems, Measurement, and Control 121, no. 3 (September 1, 1999): 402–9. http://dx.doi.org/10.1115/1.2802488.
Full textAbstract:
Bond graph models provide very useful insights into the structure of dynamic systems. One major advantage of using these models is the clear representation of constraints and independent state variables. However, certain over-constrained structures are not dealt with adequately with this approach. Such a situation arises when several energy storage elements of the same type are directly coupled by a junction structure. In these models, although the representations are legitimate in terms of physical meaning, the resultant excess states cause pitfalls in the inspection of system properties. This paper proposes the use of explicit fields to eliminate such ambiguities. It was found that the excess states caused by the topological structures can be totally eliminated by explicit fields. The excess states caused by the imposed sources then can be identified properly. Several applications are presented to illustrate the use of explicit fields.
43
Yang, Xun, Xiaoyu Du, and Meng Wang. "Learning to Match on Graph for Fashion Compatibility Modeling." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 01 (April 3, 2020): 287–94. http://dx.doi.org/10.1609/aaai.v34i01.5362.
Full textAbstract:
Understanding the mix-and-match relationships between items receives increasing attention in the fashion industry. Existing methods have primarily learned visual compatibility from dyadic co-occurrence or co-purchase information of items to model the item-item matching interaction. Despite effectiveness, rich extra-connectivities between compatible items, e.g., user-item interactions and item-item substitutable relationships, which characterize the structural properties of items, have been largely ignored. This paper presents a graph-based fashion matching framework named Deep Relational Embedding Propagation (DREP), aiming to inject the extra-connectivities between items into the pairwise compatibility modeling. Specifically, we first build a multi-relational item-item-user graph which encodes diverse item-item and user-item relationships. Then we compute structured representations of items by an attentive relational embedding propagation rule that performs messages propagation along edges of the relational graph. This leads to expressive modeling of higher-order connectivity between items and also better representation of fashion items. Finally, we predict pairwise compatibility based on a compatibility metric learning module. Extensive experiments show that DREP can significantly improve the performance of state-of-the-art methods.
44
PEYSAKHOV, MAXIM, and WILLIAM C. REGLI. "Using assembly representations to enable evolutionary design of Lego structures." Artificial Intelligence for Engineering Design, Analysis and Manufacturing 17, no. 2 (May 2003): 155–68. http://dx.doi.org/10.1017/s0890060403172046.
Full textAbstract:
This paper presents an approach to the automatic generation of electromechanical engineering designs. We apply messy genetic algorithm (GA) optimization techniques to the evolution of assemblies composed of LegoTM structures. Each design is represented as a labeled assembly graph and is evaluated based on a set of behavior and structural equations. The initial populations are generated at random, and design candidates for subsequent generations are produced by user-specified selection techniques. Crossovers are applied by using cut and splice operators at the random points of the chromosomes; random mutations are applied to modify the graph with a certain low probability. This cycle continues until a suitable design is found. The research contributions in this work include the development of a new GA encoding scheme for mechanical assemblies (Legos), as well as the creation of selection criteria for this domain. Our eventual goal is to introduce a simulation of electromechanical devices into our evaluation functions. We believe that this research creates a foundation for future work and it will apply GA techniques to the evolution of more complex and realistic electromechanical structures.
45
Zhu, Qiyao, Louis Petingi, and Tamar Schlick. "RNA-As-Graphs Motif Atlas—Dual Graph Library of RNA Modules and Viral Frameshifting-Element Applications." International Journal of Molecular Sciences 23, no. 16 (August 17, 2022): 9249. http://dx.doi.org/10.3390/ijms23169249.
Full textAbstract:
RNA motif classification is important for understanding structure/function connections and building phylogenetic relationships. Using our coarse-grained RNA-As-Graphs (RAG) representations, we identify recurrent dual graph motifs in experimentally solved RNA structures based on an improved search algorithm that finds and ranks independent RNA substructures. Our expanded list of 183 existing dual graph motifs reveals five common motifs found in transfer RNA, riboswitch, and ribosomal 5S RNA components. Moreover, we identify three motifs for available viral frameshifting RNA elements, suggesting a correlation between viral structural complexity and frameshifting efficiency. We further partition the RNA substructures into 1844 distinct submotifs, with pseudoknots and junctions retained intact. Common modules are internal loops and three-way junctions, and three submotifs are associated with riboswitches that bind nucleotides, ions, and signaling molecules. Together, our library of existing RNA motifs and submotifs adds to the growing universe of RNA modules, and provides a resource of structures and substructures for novel RNA design.
46
Saha, Aadirupa, Rakesh Shivanna, and Chiranjib Bhattacharyya. "How Many Pairwise Preferences Do We Need to Rank a Graph Consistently?" Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 4830–37. http://dx.doi.org/10.1609/aaai.v33i01.33014830.
Full textAbstract:
We consider the problem of optimal recovery of true ranking of n items from a randomly chosen subset of their pairwise preferences. It is well known that without any further assumption, one requires a sample size of Ω(n2) for the purpose. We analyze the problem with an additional structure of relational graph G([n],E) over the n items added with an assumption of locality: Neighboring items are similar in their rankings. Noting the preferential nature of the data, we choose to embed not the graph, but, its strong product to capture the pairwise node relationships. Furthermore, unlike existing literature that uses Laplacian embedding for graph based learning problems, we use a richer class of graph embeddings—orthonormal representations—that includes (normalized) Laplacian as its special case. Our proposed algorithm, Pref-Rank, predicts the underlying ranking using an SVM based approach using the chosen embedding of the product graph, and is the first to provide statistical consistency on two ranking losses: Kendall’s tau and Spearman’s footrule, with a required sample complexity of O(n2χ(G¯))⅔ pairs, χ(G¯) being the chromatic number of the complement graph G¯. Clearly, our sample complexity is smaller for dense graphs, with χ(G¯) characterizing the degree of node connectivity, which is also intuitive due to the locality assumption e.g. O(n4/3) for union of k-cliques, or O(n5/3) for random and power law graphs etc.—a quantity much smaller than the fundamental limit of Ω(n2) for large n. This, for the first time, relates ranking complexity to structural properties of the graph. We also report experimental evaluations on different synthetic and real-world datasets, where our algorithm is shown to outperform the state of the art methods.
47
Guo, Kai, Kaixiong Zhou, Xia Hu, Yu Li, Yi Chang, and Xin Wang. "Orthogonal Graph Neural Networks." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 4 (June 28, 2022): 3996–4004. http://dx.doi.org/10.1609/aaai.v36i4.20316.
Full textAbstract:
Graph neural networks (GNNs) have received tremendous attention due to their superiority in learning node representations. These models rely on message passing and feature transformation functions to encode the structural and feature information from neighbors. However, stacking more convolutional layers significantly decreases the performance of GNNs. Most recent studies attribute this limitation to the over-smoothing issue, where node embeddings converge to indistinguishable vectors. Through a number of experimental observations, we argue that the main factor degrading the performance is the unstable forward normalization and backward gradient resulted from the improper design of the feature transformation, especially for shallow GNNs where the over-smoothing has not happened. Therefore, we propose a novel orthogonal feature transformation, named Ortho-GConv, which could generally augment the existing GNN backbones to stabilize the model training and improve the model's generalization performance. Specifically, we maintain the orthogonality of the feature transformation comprehensively from three perspectives, namely hybrid weight initialization, orthogonal transformation, and orthogonal regularization. By equipping the existing GNNs (e.g. GCN, JKNet, GCNII) with Ortho-GConv, we demonstrate the generality of the orthogonal feature transformation to enable stable training, and show its effectiveness for node and graph classification tasks.
48
Xu, Yonghui, Shengjie Sun, Huiguo Zhang, Chang’an Yi, Yuan Miao, Dong Yang, Xiaonan Meng, et al. "Time-Aware Graph Embedding: A Temporal Smoothness and Task-Oriented Approach." ACM Transactions on Knowledge Discovery from Data 16, no. 3 (June 30, 2022): 1–23. http://dx.doi.org/10.1145/3480243.
Full textAbstract:
Knowledge graph embedding, which aims at learning the low-dimensional representations of entities and relationships, has attracted considerable research efforts recently. However, most knowledge graph embedding methods focus on the structural relationships in fixed triples while ignoring the temporal information. Currently, existing time-aware graph embedding methods only focus on the factual plausibility, while ignoring the temporal smoothness, which models the interactions between a fact and its contexts, and thus can capture fine-granularity temporal relationships. This leads to the limited performance of embedding related applications. To solve this problem, this article presents a Robustly Time-aware Graph Embedding (RTGE) method by incorporating temporal smoothness. Two major innovations of our article are presented here. At first, RTGE integrates a measure of temporal smoothness in the learning process of the time-aware graph embedding. Via the proposed additional smoothing factor, RTGE can preserve both structural information and evolutionary patterns of a given graph. Secondly, RTGE provides a general task-oriented negative sampling strategy associated with temporally aware information, which further improves the adaptive ability of the proposed algorithm and plays an essential role in obtaining superior performance in various tasks. Extensive experiments conducted on multiple benchmark tasks show that RTGE can increase performance in entity/relationship/temporal scoping prediction tasks.
49
Saeidi, Maham, Waldemar Karwowski, Farzad V. Farahani, Krzysztof Fiok, P. A. Hancock, Ben D. Sawyer, Leonardo Christov-Moore, and Pamela K. Douglas. "Decoding Task-Based fMRI Data with Graph Neural Networks, Considering Individual Differences." Brain Sciences 12, no. 8 (August 17, 2022): 1094. http://dx.doi.org/10.3390/brainsci12081094.
Full textAbstract:
Task fMRI provides an opportunity to analyze the working mechanisms of the human brain during specific experimental paradigms. Deep learning models have increasingly been applied for decoding and encoding purposes study to representations in task fMRI data. More recently, graph neural networks, or neural networks models designed to leverage the properties of graph representations, have recently shown promise in task fMRI decoding studies. Here, we propose an end-to-end graph convolutional network (GCN) framework with three convolutional layers to classify task fMRI data from the Human Connectome Project dataset. We compared the predictive performance of our GCN model across four of the most widely used node embedding algorithms—NetMF, RandNE, Node2Vec, and Walklets—to automatically extract the structural properties of the nodes in the functional graph. The empirical results indicated that our GCN framework accurately predicted individual differences (0.978 and 0.976) with the NetMF and RandNE embedding methods, respectively. Furthermore, to assess the effects of individual differences, we tested the classification performance of the model on sub-datasets divided according to gender and fluid intelligence. Experimental results indicated significant differences in the classification predictions of gender, but not high/low fluid intelligence fMRI data. Our experiments yielded promising results and demonstrated the superior ability of our GCN in modeling task fMRI data.
50
SHAI, OFFER. "The multidisciplinary combinatorial approach (MCA) and its applications in engineering." Artificial Intelligence for Engineering Design, Analysis and Manufacturing 15, no. 2 (April 2001): 109–44. http://dx.doi.org/10.1017/s0890060401152030.
Full textAbstract:
The current paper describes the Multidisciplinary Combinatorial Approach (MCA), the idea of which is to develop discrete mathematical representations, called “Combinatorial Representations” (CR) and to represent with them various engineering systems. During the research, the properties and methods embedded in each representation and the connections between them were investigated thoroughly, after which they were associated with various engineering systems to solve related engineering problems. The CR developed up until now are based on graph theory, matroid theory, and discrete linear programming, whereas the current paper employs only the first two. The approach opens up new ways of working with representations, reasoning and design, some of which are reported in the paper, as follows: 1) Integrated multidisciplinary representation—systems which contain interrelating elements from different disciplines are represented by the same CR. Consequently, a uniform analysis process is performed on the representation, and thus on the whole system, irrespective of the specific disciplines, to which the elements belong. 2) Deriving known methods and theorems—new proofs to known methods and theorems are derived in a new way, this time on the basis of the combinatorial theorems embedded in the CR. This enables development of a meta-representation for engineering as a whole, through which the engineering reasoning becomes convenient. In the current paper, this issue is illustrated on structural analysis. 3) Deriving novel connections between remote fields—new connections are derived on the basis of the relations between the different combinatorial representations. An innovative connection between mechanisms and trusses, shown in the paper, has been derived on the basis of the mutual dualism between their corresponding CR. This new connection alone has opened several new avenues of research, since knowledge and algorithms from machine theory are now available for use in structural analysis and vice versa. Furthermore, it has opened opportunities for developing new design methods, in which, for instance, structures with special properties are developed on the basis of known mechanisms with special properties, as demonstrated in this paper. Conversely, one can use these techniques to develop special mechanisms from known trusses.