Articles de revues sur le sujet « Graph Pooling and Convolution »
Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Graph Pooling and Convolution.
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 Pooling and Convolution ».
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
Qin, Jian, Li Liu, Hui Shen et Dewen Hu. « Uniform Pooling for Graph Networks ». Applied Sciences 10, no 18 (10 septembre 2020) : 6287. http://dx.doi.org/10.3390/app10186287.
Texte intégralRésumé :
The graph convolution network has received a lot of attention because it extends the convolution to non-Euclidean domains. However, the graph pooling method is still less concerned, which can learn coarse graph embedding to facilitate graph classification. Previous pooling methods were based on assigning a score to each node and then pooling only the highest-scoring nodes, which might throw away whole neighbourhoods of nodes and therefore information. Here, we proposed a novel pooling method UGPool with a new point-of-view on selecting nodes. UGPool learns node scores based on node features and uniformly pools neighboring nodes instead of top nodes in the score-space, resulting in a uniformly coarsened graph. In multiple graph classification tasks, including the protein graphs, the biological graphs and the brain connectivity graphs, we demonstrated that UGPool outperforms other graph pooling methods while maintaining high efficiency. Moreover, we also show that UGPool can be integrated with multiple graph convolution networks to effectively improve performance compared to no pooling.
2
Yang, Xiaowen, Yanghui Wen, Shichao Jiao, Rong Zhao, Xie Han et Ligang He. « Point Cloud Segmentation Network Based on Attention Mechanism and Dual Graph Convolution ». Electronics 12, no 24 (13 décembre 2023) : 4991. http://dx.doi.org/10.3390/electronics12244991.
Texte intégralRésumé :
To overcome the limitations of inadequate local feature representation and the underutilization of global information in dynamic graph convolutions, we propose a network that combines attention mechanisms with dual graph convolutions. Firstly, we construct a static graph based on the dynamic graph using the K-nearest neighbors algorithm and geometric distances of point clouds. This integration of dynamic and static graphs forms a dual graph structure, compensating for the underutilization of geometric positional relationships in the dynamic graph. Next, edge convolutions are applied to extract edge features from the dual graph structure. To further enhance the capturing ability of local features, we employ attention pooling, which combines max pooling and average pooling operations. Secondly, we introduce channel attention modules and spatial self-attention modules to improve the representation ability of global features and enhance semantic segmentation accuracy in our network. Experimental results on the S3DIS dataset demonstrate that compared to dynamic graph convolution alone, our proposed approach effectively utilizes both semantic and geometric relationships between point clouds using dual graph convolutions while addressing limitations related to insufficient local feature extraction. The introduction of attention mechanisms helps mitigate underutilization issues with global information, resulting in significant improvements in model performance.
3
Diao, Qi, Yaping Dai, Jiacheng Wang, Xiaoxue Feng, Feng Pan et Ce Zhang. « Spatial-Pooling-Based Graph Attention U-Net for Hyperspectral Image Classification ». Remote Sensing 16, no 6 (7 mars 2024) : 937. http://dx.doi.org/10.3390/rs16060937.
Texte intégralRésumé :
In recent years, graph convolutional networks (GCNs) have attracted increasing attention in hyperspectral image (HSI) classification owing to their exceptional representation capabilities. However, the high computational requirements of GCNs have led most existing GCN-based HSI classification methods to utilize superpixels as graph nodes, thereby limiting the spatial topology scale and neglecting pixel-level spectral–spatial features. To address these limitations, we propose a novel HSI classification network based on graph convolution called the spatial-pooling-based graph attention U-net (SPGAU). Specifically, unlike existing GCN models that rely on fixed graphs, our model involves a spatial pooling method that emulates the region-growing process of superpixels and constructs multi-level graphs by progressively merging adjacent graph nodes. Inspired by the CNN classification framework U-net, SPGAU’s model has a U-shaped structure, realizing multi-scale feature extraction from coarse to fine and gradually fusing features from different graph levels. Additionally, the proposed graph attention convolution method adaptively aggregates adjacency information, thereby further enhancing feature extraction efficiency. Moreover, a 1D-CNN is established to extract pixel-level features, striking an optimal balance between enhancing the feature quality and reducing the computational burden. Experimental results on three representative benchmark datasets demonstrate that the proposed SPGAU outperforms other mainstream models both qualitatively and quantitatively.
4
Ma, Zheng, Junyu Xuan, Yu Guang Wang, Ming Li et Pietro Liò. « Path integral based convolution and pooling for graph neural networks* ». Journal of Statistical Mechanics : Theory and Experiment 2021, no 12 (1 décembre 2021) : 124011. http://dx.doi.org/10.1088/1742-5468/ac3ae4.
Texte intégralRésumé :
Abstract Graph neural networks (GNNs) extend the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success. Borrowing ideas from physics, we propose path integral-based GNNs (PAN) for classification and regression tasks on graphs. Specifically, we consider a convolution operation that involves every path linking the message sender and receiver with learnable weights depending on the path length, which corresponds to the maximal entropy random walk. It generalizes the graph Laplacian to a new transition matrix that we call the maximal entropy transition (MET) matrix derived from a path integral formalism. Importantly, the diagonal entries of the MET matrix are directly related to the subgraph centrality, thus leading to a natural and adaptive pooling mechanism. PAN provides a versatile framework that can be tailored for different graph data with varying sizes and structures. We can view most existing GNN architectures as special cases of PAN. Experimental results show that PAN achieves state-of-the-art performance on various graph classification/regression tasks, including a new benchmark dataset from statistical mechanics that we propose to boost applications of GNN in physical sciences.
5
Li, Shenhao, Zhichon Pan, Hongyi Li, Yue Xiao, Ming Liu et Xiaorui Wang. « Convergence criterion of power flow calculation based on graph neural network ». Journal of Physics : Conference Series 2703, no 1 (1 février 2024) : 012042. http://dx.doi.org/10.1088/1742-6596/2703/1/012042.
Texte intégralRésumé :
Abstract In order to solve the problem of current data-driven power flow calculation methods rarely consider the divergence of power flow, which always maps a false system power flow when a divergence power flow case was given, a data-driven power flow convergence method based on DGAT-GPPool graph neural network classifier is proposed. Firstly, to solve the problem that the classical graph convolution method does not consider the edge attribute, a double-view graph attention convolution layer is constructed based on line admittance. Secondly, to solve the existing pooling method also does not consider the edge attribute and the loss of physical meaning of the coarse graph obtained from pooling, a grid partition pooling layer is constructed based on the electrical distance between nodes. Finally, 10000 system samples containing different network topologies are generated based on the IEEE 14-node system and its extended system, the accuracy reaches 99.3% in the testing set after training, and the effectiveness of the improvements in graph convolution and graph pooling is verified by comparative experiments.
6
Guo, Kan, Yongli Hu, Yanfeng Sun, Sean Qian, Junbin Gao et Baocai Yin. « Hierarchical Graph Convolution Network for Traffic Forecasting ». Proceedings of the AAAI Conference on Artificial Intelligence 35, no 1 (18 mai 2021) : 151–59. http://dx.doi.org/10.1609/aaai.v35i1.16088.
Texte intégralRésumé :
Traffic forecasting is attracting considerable interest due to its widespread application in intelligent transportation systems. Given the complex and dynamic traffic data, many methods focus on how to establish a spatial-temporal model to express the non-stationary traffic patterns. Recently, the latest Graph Convolution Network (GCN) has been introduced to learn spatial features while the time neural networks are used to learn temporal features. These GCN based methods obtain state-of-the-art performance. However, the current GCN based methods ignore the natural hierarchical structure of traffic systems which is composed of the micro layers of road networks and the macro layers of region networks, in which the nodes are obtained through pooling method and could include some hot traffic regions such as downtown and CBD etc., while the current GCN is only applied on the micro graph of road networks. In this paper, we propose a novel Hierarchical Graph Convolution Networks (HGCN) for traffic forecasting by operating on both the micro and macro traffic graphs. The proposed method is evaluated on two complex city traffic speed datasets. Compared to the latest GCN based methods like Graph WaveNet, the proposed HGCN gets higher traffic forecasting precision with lower computational cost.The website of the code is https://github.com/guokan987/HGCN.git.
7
Bachlechner, M., T. Birkenfeld, P. Soldin, A. Stahl et C. Wiebusch. « Partition pooling for convolutional graph network applications in particle physics ». Journal of Instrumentation 17, no 10 (1 octobre 2022) : P10004. http://dx.doi.org/10.1088/1748-0221/17/10/p10004.
Texte intégralRésumé :
Abstract Convolutional graph networks are used in particle physics for effective event reconstructions and classifications. However, their performances can be limited by the considerable amount of sensors used in modern particle detectors if applied to sensor-level data. We present a pooling scheme that uses partitioning to create pooling kernels on graphs, similar to pooling on images. Partition pooling can be used to adopt successful image recognition architectures for graph neural network applications in particle physics. The reduced computational resources allow for deeper networks and more extensive hyperparameter optimizations. To show its applicability, we construct a convolutional graph network with partition pooling that reconstructs simulated interaction vertices for an idealized neutrino detector. The pooling network yields improved performance and is less susceptible to overfitting than a similar network without pooling. The lower resource requirements allow the construction of a deeper network with further improved performance.
8
Arsini, Lorenzo, Barbara Caccia, Andrea Ciardiello, Stefano Giagu et Carlo Mancini Terracciano. « Nearest Neighbours Graph Variational AutoEncoder ». Algorithms 16, no 3 (6 mars 2023) : 143. http://dx.doi.org/10.3390/a16030143.
Texte intégralRésumé :
Graphs are versatile structures for the representation of many real-world data. Deep Learning on graphs is currently able to solve a wide range of problems with excellent results. However, both the generation of graphs and the handling of large graphs still remain open challenges. This work aims to introduce techniques for generating large graphs and test the approach on a complex problem such as the calculation of dose distribution in oncological radiotherapy applications. To this end, we introduced a pooling technique (ReNN-Pool) capable of sampling nodes that are spatially uniform without computational requirements in both model training and inference. By construction, the ReNN-Pool also allows the definition of a symmetric un-pooling operation to recover the original dimensionality of the graphs. We also present a Variational AutoEncoder (VAE) for generating graphs, based on the defined pooling and un-pooling operations, which employs convolutional graph layers in both encoding and decoding phases. The performance of the model was tested on both the realistic use case of a cylindrical graph dataset for a radiotherapy application and the standard benchmark dataset sprite. Compared to other graph pooling techniques, ReNN-Pool proved to improve both performance and computational requirements.
9
Cheung, Mark, John Shi, Oren Wright, Lavendar Y. Jiang, Xujin Liu et Jose M. F. Moura. « Graph Signal Processing and Deep Learning : Convolution, Pooling, and Topology ». IEEE Signal Processing Magazine 37, no 6 (novembre 2020) : 139–49. http://dx.doi.org/10.1109/msp.2020.3014594.
Texte intégral
10
Chen, Jiawang, et Zhenqiang Wu. « Learning Embedding for Signed Network in Social Media with Hierarchical Graph Pooling ». Applied Sciences 12, no 19 (28 septembre 2022) : 9795. http://dx.doi.org/10.3390/app12199795.
Texte intégralRésumé :
Signed network embedding concentrates on learning fixed-length representations for nodes in signed networks with positive and negative links, which contributes to many downstream tasks in social media, such as link prediction. However, most signed network embedding approaches neglect hierarchical graph pooling in the networks, limiting the capacity to learn genuine signed graph topology. To overcome this limitation, this paper presents a unique deep learning-based Signed network embedding model with Hierarchical Graph Pooling (SHGP). To be more explicit, a hierarchical pooling mechanism has been developed to encode the high-level features of the networks. Moreover, a graph convolution layer is introduced to aggregate both positive and negative information from neighbor nodes, and the concatenation of two parts generates the final embedding of the nodes. Extensive experiments on three large real-world signed network datasets demonstrate the effectiveness and excellence of the proposed method.
11
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.
12
Liu, Q., et Y. Dong. « DEEP FEATURE EXTRACTION BASED ON DYNAMIC GRAPH CONVOLUTIONAL NETWORKS FOR ACCELERATED HYPERSPECTRAL IMAGE CLASSIFICATION ». ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-3-2022 (17 mai 2022) : 139–46. http://dx.doi.org/10.5194/isprs-annals-v-3-2022-139-2022.
Texte intégralRésumé :
Abstract. Deep learning has achieved impressive results on hyperspectral images (HSIs) classification. Among them, supervised learning convolutional neural networks (CNNs) and semi-supervised learning graph neural networks (GNNs) are the two main network frameworks. However, 1) the supervised learning CNN faces the problem of high model time complexity as the number of network layers deepens; 2) the semi-supervised learning GNN faces the problem of high spatial complexity due to the computation of adjacency relations. In this paper, a novel dynamic graph convolutional HSI classification method is proposed, which is called dynamic graph convolutional networks (DGCNet). We first obtain two classification features by implementing flattening and global average pooling operation on the results of the convolution layer, which fully exploits the spatial-spectral information contained in the hyperspectral data. Then the dynamic graph convolution module is applied to extract the intrinsic structural information of each patch. Finally, HSI is classified based on spatial, spectral and structural features. DGCNet uses three branches to process multiple features of HSI in parallel and is trained in a supervised learning manner. In addition, DropBlock and label smoothing regularization techniques are applied to further improve the generalization capability of the model. Comparative experiments show that our proposed algorithm is comparable with the state-of-the art supervised learning models in terms of accuracy while also significantly outperforming in terms of time.
13
Hao, Jiao, Zongbao Zhang et Yihan Ping. « Power System Fault Diagnosis and Prediction System Based on Graph Neural Network ». International Journal of Information Technologies and Systems Approach 17, no 1 (17 janvier 2024) : 1–14. http://dx.doi.org/10.4018/ijitsa.336475.
Texte intégralRésumé :
The stability and reliability of the power system are of utmost significance in upholding the smooth functioning of modern society. Fault diagnosis and prediction represent pivotal factors in the operation and maintenance of the power system. This article presents an approach employing graph neural network (GNN) to enhance the precision and efficiency of power system fault diagnosis and prediction. The system's efficacy lies in its ability to capture the intricate interconnections and dynamic variations within the power system by conceptualizing it as a graph structure and harnessing the capabilities of GNN. In this study, the authors introduce a substitution for the pooling layer with a convolution operation. A central role is played by the global average pooling layer, connecting the convolution layer and the fully connected layer. The fully connected layer carries out nonlinear computations, ultimately providing the classification at the top-level output layer. In experiments and tests, we verified the performance of the system.
14
Bhatti, Uzair Aslam, Hao Tang, Guilu Wu, Shah Marjan et Aamir Hussain. « Deep Learning with Graph Convolutional Networks : An Overview and Latest Applications in Computational Intelligence ». International Journal of Intelligent Systems 2023 (28 février 2023) : 1–28. http://dx.doi.org/10.1155/2023/8342104.
Texte intégralRésumé :
Convolutional neural networks (CNNs) have received widespread attention due to their powerful modeling capabilities and have been successfully applied in natural language processing, image recognition, and other fields. On the other hand, traditional CNN can only deal with Euclidean spatial data. In contrast, many real-life scenarios, such as transportation networks, social networks, reference networks, and so on, exist in graph data. The creation of graph convolution operators and graph pooling is at the heart of migrating CNN to graph data analysis and processing. With the advancement of the Internet and technology, graph convolution network (GCN), as an innovative technology in artificial intelligence (AI), has received more and more attention. GCN has been widely used in different fields such as image processing, intelligent recommender system, knowledge-based graph, and other areas due to their excellent characteristics in processing non-European spatial data. At the same time, communication networks have also embraced AI technology in recent years, and AI serves as the brain of the future network and realizes the comprehensive intelligence of the future grid. Many complex communication network problems can be abstracted as graph-based optimization problems and solved by GCN, thus overcoming the limitations of traditional methods. This survey briefly describes the definition of graph-based machine learning, introduces different types of graph networks, summarizes the application of GCN in various research fields, analyzes the research status, and gives the future research direction.
15
Sun, Linhui, Yifan Zhang, Jian Cheng et Hanqing Lu. « Asynchronous Event Processing with Local-Shift Graph Convolutional Network ». Proceedings of the AAAI Conference on Artificial Intelligence 37, no 2 (26 juin 2023) : 2402–10. http://dx.doi.org/10.1609/aaai.v37i2.25336.
Texte intégralRésumé :
Event cameras are bio-inspired sensors that produce sparse and asynchronous event streams instead of frame-based images at a high-rate. Recent works utilizing graph convolutional networks (GCNs) have achieved remarkable performance in recognition tasks, which model event stream as spatio-temporal graph. However, the computational mechanism of graph convolution introduces redundant computation when aggregating neighbor features, which limits the low-latency nature of the events. And they perform a synchronous inference process, which can not achieve a fast response to the asynchronous event signals. This paper proposes a local-shift graph convolutional network (LSNet), which utilizes a novel local-shift operation equipped with a local spatio-temporal attention component to achieve efficient and adaptive aggregation of neighbor features. To improve the efficiency of pooling operation in feature extraction, we design a node-importance based parallel pooling method (NIPooling) for sparse and low-latency event data. Based on the calculated importance of each node, NIPooling can efficiently obtain uniform sampling results in parallel, which retains the diversity of event streams. Furthermore, for achieving a fast response to asynchronous event signals, an asynchronous event processing procedure is proposed to restrict the network nodes which need to recompute activations only to those affected by the new arrival event. Experimental results show that the computational cost can be reduced by nearly 9 times through using local-shift operation and the proposed asynchronous procedure can further improve the inference efficiency, while achieving state-of-the-art performance on gesture recognition and object recognition.
16
Wang, Yucheng, Yuecong Xu, Jianfei Yang, Min Wu, Xiaoli Li, Lihua Xie et Zhenghua Chen. « Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data ». Proceedings of the AAAI Conference on Artificial Intelligence 38, no 14 (24 mars 2024) : 15715–24. http://dx.doi.org/10.1609/aaai.v38i14.29500.
Texte intégralRésumé :
Multivariate Time-Series (MTS) data is crucial in various application fields. With its sequential and multi-source (multiple sensors) properties, MTS data inherently exhibits Spatial-Temporal (ST) dependencies, involving temporal correlations between timestamps and spatial correlations between sensors in each timestamp. To effectively leverage this information, Graph Neural Network-based methods (GNNs) have been widely adopted. However, existing approaches separately capture spatial dependency and temporal dependency and fail to capture the correlations between Different sEnsors at Different Timestamps (DEDT). Overlooking such correlations hinders the comprehensive modelling of ST dependencies within MTS data, thus restricting existing GNNs from learning effective representations. To address this limitation, we propose a novel method called Fully-Connected Spatial-Temporal Graph Neural Network (FC-STGNN), including two key components namely FC graph construction and FC graph convolution. For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT. Further, we devise FC graph convolution with a moving-pooling GNN layer to effectively capture the ST dependencies for learning effective representations. Extensive experiments show the effectiveness of FC-STGNN on multiple MTS datasets compared to SOTA methods. The code is available at https://github.com/Frank-Wang-oss/FCSTGNN.
17
Li, Liangwei, Lin Liu, Xiaohui Du, Xiangzhou Wang, Ziruo Zhang, Jing Zhang, Ping Zhang et Juanxiu Liu. « CGUN-2A : Deep Graph Convolutional Network via Contrastive Learning for Large-Scale Zero-Shot Image Classification ». Sensors 22, no 24 (18 décembre 2022) : 9980. http://dx.doi.org/10.3390/s22249980.
Texte intégralRésumé :
Taxonomy illustrates that natural creatures can be classified with a hierarchy. The connections between species are explicit and objective and can be organized into a knowledge graph (KG). It is a challenging task to mine features of known categories from KG and to reason on unknown categories. Graph Convolutional Network (GCN) has recently been viewed as a potential approach to zero-shot learning. GCN enables knowledge transfer by sharing the statistical strength of nodes in the graph. More layers of graph convolution are stacked in order to aggregate the hierarchical information in the KG. However, the Laplacian over-smoothing problem will be severe as the number of GCN layers deepens, which leads the features between nodes toward a tendency to be similar and degrade the performance of zero-shot image classification tasks. We consider two parts to mitigate the Laplacian over-smoothing problem, namely reducing the invalid node aggregation and improving the discriminability among nodes in the deep graph network. We propose a top-k graph pooling method based on the self-attention mechanism to control specific node aggregation, and we introduce a dual structural symmetric knowledge graph additionally to enhance the representation of nodes in the latent space. Finally, we apply these new concepts to the recently widely used contrastive learning framework and propose a novel Contrastive Graph U-Net with two Attention-based graph pooling (Att-gPool) layers, CGUN-2A, which explicitly alleviates the Laplacian over-smoothing problem. To evaluate the performance of the method on complex real-world scenes, we test it on the large-scale zero-shot image classification dataset. Extensive experiments show the positive effect of allowing nodes to perform specific aggregation, as well as homogeneous graph comparison, in our deep graph network. We show how it significantly boosts zero-shot image classification performance. The Hit@1 accuracy is 17.5% relatively higher than the baseline model on the ImageNet21K dataset.
18
Hu, Ruiqi, Shirui Pan, Guodong Long, Qinghua Lu, Liming Zhu et Jing Jiang. « Going Deep : Graph Convolutional Ladder-Shape Networks ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 03 (3 avril 2020) : 2838–45. http://dx.doi.org/10.1609/aaai.v34i03.5673.
Texte intégralRésumé :
Neighborhood aggregation algorithms like spectral graph convolutional networks (GCNs) formulate graph convolutions as a symmetric Laplacian smoothing operation to aggregate the feature information of one node with that of its neighbors. While they have achieved great success in semi-supervised node classification on graphs, current approaches suffer from the over-smoothing problem when the depth of the neural networks increases, which always leads to a noticeable degradation of performance. To solve this problem, we present graph convolutional ladder-shape networks (GCLN), a novel graph neural network architecture that transmits messages from shallow layers to deeper layers to overcome the over-smoothing problem and dramatically extend the scale of the neural networks with improved performance. We have validated the effectiveness of proposed GCLN at a node-wise level with a semi-supervised task (node classification) and an unsupervised task (node clustering), and at a graph-wise level with graph classification by applying a differentiable pooling operation. The proposed GCLN outperforms original GCNs, deep GCNs and other state-of-the-art GCN-based models for all three tasks, which were designed from various perspectives on six real-world benchmark data sets.
19
Wang, Yu, Liang Hu, Yang Wu et Wanfu Gao. « Graph Multihead Attention Pooling with Self-Supervised Learning ». Entropy 24, no 12 (29 novembre 2022) : 1745. http://dx.doi.org/10.3390/e24121745.
Texte intégralRésumé :
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.
20
Han, Xiao, Jing Peng, Tailai Peng, Rui Chen, Boyuan Hou, Xinran Xie et Zhe Cui. « The Status and Trend of Chinese News Forecast Based on Graph Convolutional Network Pooling Algorithm ». Applied Sciences 12, no 2 (17 janvier 2022) : 900. http://dx.doi.org/10.3390/app12020900.
Texte intégralRésumé :
It is always a hot issue in the intelligence analysis field to predict the trend of news description by pre-trained language models and graph neural networks. However, there are several problems in the existing research: (1) there are few Chinese data sets on this subject in academia and industry; and (2) using the existing pre-trained language models and graph classification algorithms cannot achieve satisfactory results. The method described in this paper can better solve these problems. (1) We built a Chinese news database predicted by more than 9000 annotated news time trends, filling the gaps in this database. (2) We designed an improved method based on the pre-trained language model and graph neural networks pooling algorithm. In the graph pooling algorithm, the Graph U-Nets Pooling method and self-attention are combined, which can better solve the analysis of the problem of forecasting the development trend of news events. The experimental results show that the effect of this method compared with the baseline graph classification algorithm is improved, and it also solves the shortcomings of the pre-trained language model that cannot handle very long texts. Therefore, it can be concluded that our research has strong processing capabilities for analyzing and predicting the development trend of Chinese news events.
21
Pham, Hai Van, Dat Hoang Thanh et Philip Moore. « Hierarchical Pooling in Graph Neural Networks to Enhance Classification Performance in Large Datasets ». Sensors 21, no 18 (10 septembre 2021) : 6070. http://dx.doi.org/10.3390/s21186070.
Texte intégralRésumé :
Deep learning methods predicated on convolutional neural networks and graph neural networks have enabled significant improvement in node classification and prediction when applied to graph representation with learning node embedding to effectively represent the hierarchical properties of graphs. An interesting approach (DiffPool) utilises a differentiable graph pooling technique which learns ‘differentiable soft cluster assignment’ for nodes at each layer of a deep graph neural network with nodes mapped on sets of clusters. However, effective control of the learning process is difficult given the inherent complexity in an ‘end-to-end’ model with the potential for a large number parameters (including the potential for redundant parameters). In this paper, we propose an approach termed FPool, which is a development of the basic method adopted in DiffPool (where pooling is applied directly to node representations). Techniques designed to enhance data classification have been created and evaluated using a number of popular and publicly available sensor datasets. Experimental results for FPool demonstrate improved classification and prediction performance when compared to alternative methods considered. Moreover, FPool shows a significant reduction in the training time over the basic DiffPool framework.
22
Duan, Yutai, Jianming Wang, Haoran Ma et Yukuan Sun. « Residual convolutional graph neural network with subgraph attention pooling ». Tsinghua Science and Technology 27, no 4 (août 2022) : 653–63. http://dx.doi.org/10.26599/tst.2021.9010058.
Texte intégral
23
Zhang, Shuoyan, Jiacheng Yang, Ying Zhang, Jiayi Zhong, Wenjing Hu, Chenyang Li et Jiehui Jiang. « The Combination of a Graph Neural Network Technique and Brain Imaging to Diagnose Neurological Disorders : A Review and Outlook ». Brain Sciences 13, no 10 (16 octobre 2023) : 1462. http://dx.doi.org/10.3390/brainsci13101462.
Texte intégralRésumé :
Neurological disorders (NDs), such as Alzheimer’s disease, have been a threat to human health all over the world. It is of great importance to diagnose ND through combining artificial intelligence technology and brain imaging. A graph neural network (GNN) can model and analyze the brain, imaging from morphology, anatomical structure, function features, and other aspects, thus becoming one of the best deep learning models in the diagnosis of ND. Some researchers have investigated the application of GNN in the medical field, but the scope is broad, and its application to NDs is less frequent and not detailed enough. This review focuses on the research progress of GNNs in the diagnosis of ND. Firstly, we systematically investigated the GNN framework of ND, including graph construction, graph convolution, graph pooling, and graph prediction. Secondly, we investigated common NDs using the GNN diagnostic model in terms of data modality, number of subjects, and diagnostic accuracy. Thirdly, we discussed some research challenges and future research directions. The results of this review may be a valuable contribution to the ongoing intersection of artificial intelligence technology and brain imaging.
24
Yang, Yukun, Bo Ma, Xiangdong Liu, Liang Zhao et Shoudong Huang. « GSAP : A Global Structure Attention Pooling Method for Graph-Based Visual Place Recognition ». Remote Sensing 13, no 8 (10 avril 2021) : 1467. http://dx.doi.org/10.3390/rs13081467.
Texte intégralRésumé :
The Visual Place Recognition problem aims to use an image to recognize the location that has been visited before. In most of the scenes revisited, the appearance and view are drastically different. Most previous works focus on the 2-D image-based deep learning method. However, the convolutional features are not robust enough to the challenging scenes mentioned above. In this paper, in order to take advantage of the information that helps the Visual Place Recognition task in these challenging scenes, we propose a new graph construction approach to extract the useful information from an RGB image and a depth image and fuse them in graph data. Then, we deal with the Visual Place Recognition problem as a graph classification problem. We propose a new Global Pooling method—Global Structure Attention Pooling (GSAP), which improves the classification accuracy by improving the expression ability of the Global Pooling component. The experiments show that our GSAP method improves the accuracy of graph classification by approximately 2–5%, the graph construction method improves the accuracy of graph classification by approximately 4–6%, and that the whole Visual Place Recognition model is robust to appearance change and view change.
25
Ma, Tianle, et Aidong Zhang. « AffinityNet : Semi-Supervised Few-Shot Learning for Disease Type Prediction ». Proceedings of the AAAI Conference on Artificial Intelligence 33 (17 juillet 2019) : 1069–76. http://dx.doi.org/10.1609/aaai.v33i01.33011069.
Texte intégralRésumé :
While deep learning has achieved great success in computer vision and many other fields, currently it does not work very well on patient genomic data with the “big p, small N” problem (i.e., a relatively small number of samples with highdimensional features). In order to make deep learning work with a small amount of training data, we have to design new models that facilitate few-shot learning. Here we present the Affinity Network Model (AffinityNet), a data efficient deep learning model that can learn from a limited number of training examples and generalize well. The backbone of the AffinityNet model consists of stacked k-Nearest-Neighbor (kNN) attention pooling layers. The kNN attention pooling layer is a generalization of the Graph Attention Model (GAM), and can be applied to not only graphs but also any set of objects regardless of whether a graph is given or not. As a new deep learning module, kNN attention pooling layers can be plugged into any neural network model just like convolutional layers. As a simple special case of kNN attention pooling layer, feature attention layer can directly select important features that are useful for classification tasks. Experiments on both synthetic data and cancer genomic data from TCGA projects show that our AffinityNet model has better generalization power than conventional neural network models with little training data.
26
Hou, Wentai, Lequan Yu, Chengxuan Lin, Helong Huang, Rongshan Yu, Jing Qin et Liansheng Wang. « H^2-MIL : Exploring Hierarchical Representation with Heterogeneous Multiple Instance Learning for Whole Slide Image Analysis ». Proceedings of the AAAI Conference on Artificial Intelligence 36, no 1 (28 juin 2022) : 933–41. http://dx.doi.org/10.1609/aaai.v36i1.19976.
Texte intégralRésumé :
Current representation learning methods for whole slide image (WSI) with pyramidal resolutions are inherently homogeneous and flat, which cannot fully exploit the multiscale and heterogeneous diagnostic information of different structures for comprehensive analysis. This paper presents a novel graph neural network-based multiple instance learning framework (i.e., H^2-MIL) to learn hierarchical representation from a heterogeneous graph with different resolutions for WSI analysis. A heterogeneous graph with the “resolution” attribute is constructed to explicitly model the feature and spatial-scaling relationship of multi-resolution patches. We then design a novel resolution-aware attention convolution (RAConv) block to learn compact yet discriminative representation from the graph, which tackles the heterogeneity of node neighbors with different resolutions and yields more reliable message passing. More importantly, to explore the task-related structured information of WSI pyramid, we elaborately design a novel iterative hierarchical pooling (IHPool) module to progressively aggregate the heterogeneous graph based on scaling relationships of different nodes. We evaluated our method on two public WSI datasets from the TCGA project, i.e., esophageal cancer and kidney cancer. Experimental results show that our method clearly outperforms the state-of-the-art methods on both tumor typing and staging tasks.
27
Yan, Jiayi, Shaohui Wang, Jing Lin, Peihao Li, Ruxin Zhang et Haoqian Wang. « GaitSG : Gait Recognition with SMPLs in Graph Structure ». Sensors 23, no 20 (22 octobre 2023) : 8627. http://dx.doi.org/10.3390/s23208627.
Texte intégralRésumé :
Gait recognition aims to identify a person based on his unique walking pattern. Compared with silhouettes and skeletons, skinned multi-person linear (SMPL) models can simultaneously provide human pose and shape information and are robust to viewpoint and clothing variances. However, previous approaches have only considered SMPL parameters as a whole and are yet to explore their potential for gait recognition thoroughly. To address this problem, we concentrate on SMPL representations and propose a novel SMPL-based method named GaitSG for gait recognition, which takes SMPL parameters in the graph structure as input. Specifically, we represent the SMPL model as graph nodes and employ graph convolution techniques to effectively model the human model topology and generate discriminative gait features. Further, we utilize prior knowledge of the human body and elaborately design a novel part graph pooling block, PGPB, to encode viewpoint information explicitly. The PGPB also alleviates the physical distance-unaware limitation of the graph structure. Comprehensive experiments on public gait recognition datasets, Gait3D and CASIA-B, demonstrate that GaitSG can achieve better performance and faster convergence than existing model-based approaches. Specifically, compared with the baseline SMPLGait (3D only), our model achieves approximately twice the Rank-1 accuracy and requires three times fewer training iterations on Gait3D.
28
Yan, Xiongfeng, et Min Yang. « A Comparative Study of Various Deep Learning Approaches to Shape Encoding of Planar Geospatial Objects ». ISPRS International Journal of Geo-Information 11, no 10 (18 octobre 2022) : 527. http://dx.doi.org/10.3390/ijgi11100527.
Texte intégralRésumé :
The shape encoding of geospatial objects is a key problem in the fields of cartography and geoscience. Although traditional geometric-based methods have made great progress, deep learning techniques offer a development opportunity for this classical problem. In this study, a shape encoding framework based on a deep encoder–decoder architecture was proposed, and three different methods for encoding planar geospatial shapes, namely GraphNet, SeqNet, and PixelNet methods, were constructed based on raster-based, graph-based, and sequence-based modeling for shape. The three methods were compared with the existing deep learning-based shape encoding method and two traditional geometric methods. Quantitative evaluation and visual inspection led to the following conclusions: (1) The deep encoder–decoder methods can effectively compute shape features and obtain meaningful shape coding to support the shape measure and retrieval task. (2) Compared with the traditional Fourier transform and turning function methods, the deep encoder–decoder methods showed certain advantages. (3) Compared with the SeqNet and PixelNet methods, GraphNet performed better due to the use of a graph to model the topological relations between nodes and efficient graph convolution and pooling operations to process the node features.
29
Shao, Dangguo, Zihan He, Hongbo Fan et Kun Sun. « Detection of Cattle Key Parts Based on the Improved Yolov5 Algorithm ». Agriculture 13, no 6 (23 mai 2023) : 1110. http://dx.doi.org/10.3390/agriculture13061110.
Texte intégralRésumé :
Accurate detection of key body parts of cattle is of great significance to Precision Livestock Farming (PLF), using artificial intelligence for video analysis. As the background image in cattle livestock farms is complex and the target features of the cattle are not obvious, traditional object-detection algorithms cannot detect the key parts of the image with high precision. This paper proposes the Filter_Attention attention mechanism to detect the key parts of cattle. Since the image is unstable during training and initialization, particle noise is generated in the feature graph after convolution calculation. Therefore, this paper proposes an attentional mechanism based on bilateral filtering to reduce this interference. We also designed a Pooling_Module, based on the soft pooling algorithm, which facilitates information loss relative to the initial activation graph compared to maximum pooling. Our data set contained 1723 images of cattle, in which labels of the body, head, legs, and tail were manually entered. This dataset was divided into a training set, verification set, and test set at a ratio of 7:2:1 for training the model proposed in this paper. The detection effect of our proposed module is proven by the ablation experiment from mAP, the AP value, and the F1 value. This paper also compares other mainstream object detection algorithms. The experimental results show that our model obtained 90.74% mAP, and the F1 value and AP value of the four parts were improved.
30
Hu, Kai, Jiasheng Wu, Yaogen Li, Meixia Lu, Liguo Weng et Min Xia. « FedGCN : Federated Learning-Based Graph Convolutional Networks for Non-Euclidean Spatial Data ». Mathematics 10, no 6 (21 mars 2022) : 1000. http://dx.doi.org/10.3390/math10061000.
Texte intégralRésumé :
Federated Learning (FL) can combine multiple clients for training and keep client data local, which is a good way to protect data privacy. There are many excellent FL algorithms. However, most of these can only process data with regular structures, such as images and videos. They cannot process non-Euclidean spatial data, that is, irregular data. To address this problem, we propose a Federated Learning-Based Graph Convolutional Network (FedGCN). First, we propose a Graph Convolutional Network (GCN) as a local model of FL. Based on the classical graph convolutional neural network, TopK pooling layers and full connection layers are added to this model to improve the feature extraction ability. Furthermore, to prevent pooling layers from losing information, cross-layer fusion is used in the GCN, giving FL an excellent ability to process non-Euclidean spatial data. Second, in this paper, a federated aggregation algorithm based on an online adjustable attention mechanism is proposed. The trainable parameter ρ is introduced into the attention mechanism. The aggregation method assigns the corresponding attention coefficient to each local model, which reduces the damage caused by the inefficient local model parameters to the global model and improves the fault tolerance and accuracy of the FL algorithm. Finally, we conduct experiments on six non-Euclidean spatial datasets to verify that the proposed algorithm not only has good accuracy but also has a certain degree of generality. The proposed algorithm can also perform well in different graph neural networks.
31
Embarcadero-Ruiz, Daniel, Helena Gómez-Adorno, Alberto Embarcadero-Ruiz et Gerardo Sierra. « Graph-Based Siamese Network for Authorship Verification ». Mathematics 10, no 2 (17 janvier 2022) : 277. http://dx.doi.org/10.3390/math10020277.
Texte intégralRésumé :
In this work, we propose a novel approach to solve the authorship identification task on a cross-topic and open-set scenario. Authorship verification is the task of determining whether or not two texts were written by the same author. We model the documents in a graph representation and then a graph neural network extracts relevant features from these graph representations. We present three strategies to represent the texts as graphs based on the co-occurrence of the POS labels of words. We propose a Siamese Network architecture composed of graph convolutional networks along with pooling and classification layers. We present different variants of the architecture and discuss the performance of each one. To evaluate our approach we used a collection of fanfiction texts provided by the PAN@CLEF 2021 shared task in two settings: a “small” corpus and a “large” corpus. Our graph-based approach achieved average scores (AUC ROC, F1, Brier score, F0.5u, and C@1) between 90% and 92.83% when training on the “small” and “large” corpus, respectively. Our model obtain results comparable to those of the state of the art in this task and greater than traditional baselines.
32
Lu, Zhengqiu, Chunliang Zhou, Xuyang Xuyang et Weipeng Zhang. « Face Detection and Recognition Method Based on Improved Convolutional Neural Network ». International Journal of Circuits, Systems and Signal Processing 15 (30 juillet 2021) : 774–81. http://dx.doi.org/10.46300/9106.2021.15.85.
Texte intégralRésumé :
with rapid development of deep learning technology, face recognition based on deep convolutional neural network becomes one of the main research methods. In order to solve the problems of information loss and equal treatment of each element in the input feature graph in the traditional pooling method of convolutional neural network, a face recognition algorithm based on convolutional neural network is proposed in this paper. First, MTCNN algorithm is used to detect the faces and do gray processing, and then a local weighted average pooling method based on local concern strategy is designed and a convolutional neural network based on VGG16 to recognize faces is constructed which is finally compared with common convolutional neural network. The experimental results show that this method has good face recognition accuracy in common face databases.
33
Zhao, Hongyu, Jiazhi Xie et Hongbin Wang. « Graph Convolutional Network Based on Multi-Head Pooling for Short Text Classification ». IEEE Access 10 (2022) : 11947–56. http://dx.doi.org/10.1109/access.2022.3146303.
Texte intégral
34
Du, Yinan, Jian Tang, Ting Rui, Xinxin Li et Chengsong Yang. « GBP : Graph convolutional network embedded in bilinear pooling for fine-grained encoding ». Computers and Electrical Engineering 116 (mai 2024) : 109158. http://dx.doi.org/10.1016/j.compeleceng.2024.109158.
Texte intégral
35
Pang, Bo, Zhongtian Zheng, Guoping Wang et Peng-Shuai Wang. « Learning the Geodesic Embedding with Graph Neural Networks ». ACM Transactions on Graphics 42, no 6 (5 décembre 2023) : 1–12. http://dx.doi.org/10.1145/3618317.
Texte intégralRésumé :
We present GEGNN, a learning-based method for computing the approximate geodesic distance between two arbitrary points on discrete polyhedra surfaces with constant time complexity after fast precomputation. Previous relevant methods either focus on computing the geodesic distance between a single source and all destinations, which has linear complexity at least or require a long precomputation time. Our key idea is to train a graph neural network to embed an input mesh into a high-dimensional embedding space and compute the geodesic distance between a pair of points using the corresponding embedding vectors and a lightweight decoding function. To facilitate the learning of the embedding, we propose novel graph convolution and graph pooling modules that incorporate local geodesic information and are verified to be much more effective than previous designs. After training, our method requires only one forward pass of the network per mesh as precomputation. Then, we can compute the geodesic distance between a pair of points using our decoding function, which requires only several matrix multiplications and can be massively parallelized on GPUs. We verify the efficiency and effectiveness of our method on ShapeNet and demonstrate that our method is faster than existing methods by orders of magnitude while achieving comparable or better accuracy. Additionally, our method exhibits robustness on noisy and incomplete meshes and strong generalization ability on out-of-distribution meshes. The code and pretrained model can be found on https://github.com/IntelligentGeometry/GeGnn.
36
Lei, Fangyuan, Xun Liu, Qingyun Dai, Bingo Wing-Kuen Ling, Huimin Zhao et Yan Liu. « Hybrid Low-Order and Higher-Order Graph Convolutional Networks ». Computational Intelligence and Neuroscience 2020 (23 juin 2020) : 1–9. http://dx.doi.org/10.1155/2020/3283890.
Texte intégralRésumé :
With the higher-order neighborhood information of a graph network, the accuracy of graph representation learning classification can be significantly improved. However, the current higher-order graph convolutional networks have a large number of parameters and high computational complexity. Therefore, we propose a hybrid lower-order and higher-order graph convolutional network (HLHG) learning model, which uses a weight sharing mechanism to reduce the number of network parameters. To reduce the computational complexity, we propose a novel information fusion pooling layer to combine the high-order and low-order neighborhood matrix information. We theoretically compare the computational complexity and the number of parameters of the proposed model with those of the other state-of-the-art models. Experimentally, we verify the proposed model on large-scale text network datasets using supervised learning and on citation network datasets using semisupervised learning. The experimental results show that the proposed model achieves higher classification accuracy with a small set of trainable weight parameters.
37
Huang, Linjiang, Yan Huang, Wanli Ouyang et Liang Wang. « Part-Level Graph Convolutional Network for Skeleton-Based Action Recognition ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 07 (3 avril 2020) : 11045–52. http://dx.doi.org/10.1609/aaai.v34i07.6759.
Texte intégralRésumé :
Recently, graph convolutional networks have achieved remarkable performance for skeleton-based action recognition. In this work, we identify a problem posed by the GCNs for skeleton-based action recognition, namely part-level action modeling. To address this problem, a novel Part-Level Graph Convolutional Network (PL-GCN) is proposed to capture part-level information of skeletons. Different from previous methods, the partition of body parts is learnable rather than manually defined. We propose two part-level blocks, namely Part Relation block (PR block) and Part Attention block (PA block), which are achieved by two differentiable operations, namely graph pooling operation and graph unpooling operation. The PR block aims at learning high-level relations between body parts while the PA block aims at highlighting the important body parts in the action. Integrating the original GCN with the two blocks, the PL-GCN can learn both part-level and joint-level information of the action. Extensive experiments on two benchmark datasets show the state-of-the-art performance on skeleton-based action recognition and demonstrate the effectiveness of the proposed method.
38
Yang, Rong, Junyu Niu, Ying Xu, Yun Wang et Li Qiu. « Action Recognition Based on GCN with Adjacency Matrix Generation Module and Time Domain Attention Mechanism ». Symmetry 15, no 10 (23 octobre 2023) : 1954. http://dx.doi.org/10.3390/sym15101954.
Texte intégralRésumé :
Different from other computer vision tasks, action recognition needs to process larger-scale video data. How to extract and analyze the effective parts from a huge amount of video information is the main difficulty of action recognition technology. In recent years, due to the outstanding performance of Graph Convolutional Networks (GCN) in many fields, a new solution to the action recognition algorithm has emerged. However, in current GCN models, the constant physical adjacency matrix makes it difficult to mine synergistic relationships between key points that are not directly connected in physical space. Additionally, a simple time connection of skeleton data from different frames makes each frame in the video contribute equally to the recognition results, which increases the difficulty of distinguishing action stages. In this paper, the information extraction ability of the model has been optimized in the space domain and time domain, respectively. In the space domain, an Adjacency Matrix Generation (AMG) module, which can pre-analyze node sets and generate an adaptive adjacency matrix, has been proposed. The adaptive adjacency matrix can help the graph convolution model to extract the synergistic information between the key points that are crucial for recognition. In the time domain, the Time Domain Attention (TDA) mechanism has been designed to calculate the time-domain weight vector through double pooling channels and complete the weights of key point sequences. Furthermore, performance of the improved TDA-AMG-GCN modules has been verified on the NTU-RGB+D dataset. Its detection accuracy at the CS and CV divisions reached 84.5% and 89.8%, respectively, with an average level higher than other commonly used detection methods at present.
39
Chen, Yuxin, Gaoqun Ma, Chunfeng Yuan, Bing Li, Hui Zhang, Fangshi Wang et Weiming Hu. « Graph convolutional network with structure pooling and joint-wise channel attention for action recognition ». Pattern Recognition 103 (juillet 2020) : 107321. http://dx.doi.org/10.1016/j.patcog.2020.107321.
Texte intégral
40
Andriyanov, Nikita. « Application of Graph Structures in Computer Vision Tasks ». Mathematics 10, no 21 (29 octobre 2022) : 4021. http://dx.doi.org/10.3390/math10214021.
Texte intégralRésumé :
On the one hand, the solution of computer vision tasks is associated with the development of various kinds of images or random fields mathematical models, i.e., algorithms, that are called traditional image processing. On the other hand, nowadays, deep learning methods play an important role in image recognition tasks. Such methods are based on convolutional neural networks that perform many matrix multiplication operations with model parameters and local convolutions and pooling operations. However, the modern artificial neural network architectures, such as transformers, came to the field of machine vision from natural language processing. Image transformers operate with embeddings, in the form of mosaic blocks of picture and the links between them. However, the use of graph methods in the design of neural networks can also increase efficiency. In this case, the search for hyperparameters will also include an architectural solution, such as the number of hidden layers and the number of neurons for each layer. The article proposes to use graph structures to develop simple recognition networks on different datasets, including small unbalanced X-ray image datasets, widely known the CIFAR-10 dataset and the Kaggle competition Dogs vs Cats dataset. Graph methods are compared with various known architectures and with networks trained from scratch. In addition, an algorithm for representing an image in the form of graph lattice segments is implemented, for which an appropriate description is created, based on graph data structures. This description provides quite good accuracy and performance of recognition. The effectiveness of this approach based, on the descriptors of the resulting segments, is shown, as well as the graph methods for the architecture search.
41
Ji, Xiujuan, Lei Liu et Jingwen Zhu. « Code Clone Detection with Hierarchical Attentive Graph Embedding ». International Journal of Software Engineering and Knowledge Engineering 31, no 06 (juin 2021) : 837–61. http://dx.doi.org/10.1142/s021819402150025x.
Texte intégralRésumé :
Code clone serves as a typical programming manner that reuses the existing code to solve similar programming problems, which greatly facilitates software development but recurs program bugs and maintenance costs. Recently, deep learning-based detection approaches gradually present their effectiveness on feature representation and detection performance. Among them, deep learning approaches based on abstract syntax tree (AST) construct models relying on the node embedding technique. In AST, the semantic of nodes is obviously hierarchical, and the importance of nodes is quite different to determine whether the two code fragments are cloned or not. However, some approaches do not fully consider the hierarchical structure information of source code. Some approaches ignore the different importance of nodes when generating the features of source code. Thirdly, when the tree is very large and deep, many approaches are vulnerable to the gradient vanishing problem during training. In order to properly address these challenges, we propose a hierarchical attentive graph neural network embedding model-HAG for the code clone detection. Firstly, the attention mechanism is applied on nodes in AST to distinguish the importance of different nodes during the model training. In addition, the HAG adopts graph convolutional network (GCN) to propagate the code message on AST graph and then exploits a hierarchical differential pooling GCN to sufficiently capture the code semantics at different structure level. To evaluate the effectiveness of HAG, we conducted extensive experiments on public clone dataset and compared it with seven state-of-the-art clone detection models. The experimental results demonstrate that the HAG achieves superior detection performance compared with baseline models. Especially, in the detection of moderately Type-3 or Type-4 clones, the HAG particularly outperforms baselines, indicating the strong detection capability of HAG for semantic clones. Apart from that, the impacts of the hierarchical pooling, attention mechanism and critical model parameters are systematically discussed.
42
Han, Xianquan, Xijiang Chen, Hui Deng, Peng Wan et Jianzhou Li. « Point Cloud Deep Learning Network Based on Local Domain Multi-Level Feature ». Applied Sciences 13, no 19 (28 septembre 2023) : 10804. http://dx.doi.org/10.3390/app131910804.
Texte intégralRésumé :
Point cloud deep learning networks have been widely applied in point cloud classification, part segmentation and semantic segmentation. However, current point cloud deep learning networks are insufficient in the local feature extraction of the point cloud, which affects the accuracy of point cloud classification and segmentation. To address this issue, this paper proposes a local domain multi-level feature fusion point cloud deep learning network. First, dynamic graph convolutional operation is utilized to obtain the local neighborhood feature of the point cloud. Then, relation-shape convolution is used to extract a deeper-level edge feature of the point cloud, and max pooling is adopted to aggregate the edge features. Finally, point cloud classification and segmentation are realized based on global features and local features. We use the ModelNet40 and ShapeNet datasets to conduct the comparison experiment, which is a large-scale 3D CAD model dataset and a richly annotated, large-scale dataset of 3D shapes. For ModelNet40, the overall accuracy (OA) of the proposed method is similar to DGCNN, RS-CNN, PointConv and GAPNet, all exceeding 92%. Compared to PointNet, PointNet++, SO-Net and MSHANet, the OA of the proposed method is improved by 5%, 2%, 3% and 2.6%, respectively. For the ShapeNet dataset, the mean Intersection over Union (mIoU) of the part segmentation achieved by the proposed method is 86.3%, which is 2.9%, 1.4%, 1.7%, 1.7%, 1.2%, 0.1% and 1.0% higher than PointNet, RS-Net, SCN, SPLATNet, DGCNN, RS-CNN and LRC-NET, respectively.
43
Liu, Xun, Guoqing Xia, Fangyuan Lei, Yikuan Zhang et Shihui Chang. « Higher-Order Graph Convolutional Networks With Multi-Scale Neighborhood Pooling for Semi-Supervised Node Classification ». IEEE Access 9 (2021) : 31268–75. http://dx.doi.org/10.1109/access.2021.3060173.
Texte intégral
44
Pal, Monalin, et Rubini P. « Fusion of Brain Imaging Data with Artificial Intelligence to detect Autism Spectrum Disorder ». Fusion : Practice and Applications 14, no 2 (2024) : 89–96. http://dx.doi.org/10.54216/fpa.140207.
Texte intégralRésumé :
Autism, a developmental and neurological disorder, impacts communication, interaction, and behavior, setting individuals with it apart from those without. This spectrum disorder affects various aspects of an individual's life, including social, cognitive, emotional, and physical health. Early detection and intervention are crucial for symptom reduction and facilitating learning and development. Recent advancements in machine learning and deep learning have facilitated the diagnosis of Autism by analyzing brain signals. This current study introduces an approach for Autism detection utilizing functional Magnetic Resonance Imaging (fMRI) data. The Autism Brain Imaging Data Exchange (ABIDE) dataset serves as the foundation, employing hierarchical graph pooling to abstract brain images into a graph structure. Graph Convolutional Networks are then used to learn node embeddings derived from sparse feature vectors. The model attains an accuracy of 87% on the 10-fold cross-validation dataset. This study proves to be cost-effective and efficient in identifying Autism through fMRI, making it suitable for near real-time applications.
45
Rodziewicz-Bielewicz, Jan, et Marcin Korzeń. « Comparison of Graph Fitting and Sparse Deep Learning Model for Robot Pose Estimation ». Sensors 22, no 17 (29 août 2022) : 6518. http://dx.doi.org/10.3390/s22176518.
Texte intégralRésumé :
The paper presents a simple, yet robust computer vision system for robot arm tracking with the use of RGB-D cameras. Tracking means to measure in real time the robot state given by three angles and with known restrictions about the robot geometry. The tracking system consists of two parts: image preprocessing and machine learning. In the machine learning part, we compare two approaches: fitting the robot pose to the point cloud and fitting the convolutional neural network model to the sparse 3D depth images. The advantage of the presented approach is direct use of the point cloud transformed to the sparse image in the network input and use of sparse convolutional and pooling layers (sparse CNN). The experiments confirm that the robot tracking is performed in real time and with an accuracy comparable to the accuracy of the depth sensor.
46
Yang, Boming. « Image processing based on neural networks ». Applied and Computational Engineering 10, no 1 (25 septembre 2023) : 272–81. http://dx.doi.org/10.54254/2755-2721/10/20230193.
Texte intégralRésumé :
This article integrates convolutional neural network (CNN) and graph convolutional network (GCN) techniques. Performance is improved by the suggested architecture's use of crucial methods such as dropout, batch normalization, and rank-based random pooling. The network was trained and tested on a sizable amount of breast lesion imaging data, and its precision was evaluated in comparison to other methods. The findings showed a significant increase in accuracy, resulting in high rates of malignant lesion diagnosis with few false positives. The effective fusion of CNN and GCN methods highlights the potential for improving the detection of malignant breast lesions and provides a viable path for further study in this area.
47
Luo, Wanli, et Jialiang Wang. « The Application of A-CNN in Crowd Counting of Scenic Spots ». Journal of Advanced Computational Intelligence and Intelligent Informatics 23, no 2 (20 mars 2019) : 305–8. http://dx.doi.org/10.20965/jaciii.2019.p0305.
Texte intégralRésumé :
In places where people are concentrated, such as scenic spots, the statistical accuracy of existing crowd statistics algorithms is not enough. In order to solve this problem, a crowd counting algorithm based on adaptive convolution neural network (A-CNN) is proposed, which is based on video monitoring technology. The process of its pooling is dynamically adjusted according to different feature graphs. Then the pooled weights are adjusted adaptively according to the contents of each pooled domain. Therefore, CNN can extract more accurate features when processing different pooled domains under different iteration times, so as to achieve adaptive effect finally. The experimental results show that the proposed A-CNN algorithm has improved the recognition accuracy.
48
Gu, Jindong. « Interpretable Graph Capsule Networks for Object Recognition ». Proceedings of the AAAI Conference on Artificial Intelligence 35, no 2 (18 mai 2021) : 1469–77. http://dx.doi.org/10.1609/aaai.v35i2.16237.
Texte intégralRésumé :
Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create explanations for individual classifications of CapsNets has not been well explored. The widely used saliency methods are mainly proposed for explaining CNN-based classifications; they create saliency map explanations by combining activation values and the corresponding gradients, e.g., Grad-CAM. These saliency methods require a specific architecture of the underlying classifiers and cannot be trivially applied to CapsNets due to the iterative routing mechanism therein. To overcome the lack of interpretability, we can either propose new post-hoc interpretation methods for CapsNets or modifying the model to have build-in explanations. In this work, we explore the latter. Specifically, we propose interpretable Graph Capsule Networks (GraCapsNets), where we replace the routing part with a multi-head attention-based Graph Pooling approach. In the proposed model, individual classification explanations can be created effectively and efficiently. Our model also demonstrates some unexpected benefits, even though it replaces the fundamental part of CapsNets. Our GraCapsNets achieve better classification performance with fewer parameters and better adversarial robustness, when compared to CapsNets. Besides, GraCapsNets also keep other advantages of CapsNets, namely, disentangled representations and affine transformation robustness.
49
Liu, Chao, Buhong Wang, Zhen Wang, Jiwei Tian, Peng Luo et Yong Yang. « TCFLTformer : TextCNN-Flat-Lattice Transformer for Entity Recognition of Air Traffic Management Cyber Threat Knowledge Graphs ». Aerospace 10, no 8 (7 août 2023) : 697. http://dx.doi.org/10.3390/aerospace10080697.
Texte intégralRésumé :
With the development of the air traffic management system (ATM), the cyber threat for ATM is becoming more and more serious. The recognition of ATM cyber threat entities is an important task, which can help ATM security experts quickly and accurately recognize threat entities, providing data support for the later construction of knowledge graphs, and ensuring the security and stability of ATM. The entity recognition methods are mainly based on traditional machine learning in a period of time; however, the methods have problems such as low recall and low accuracy. Moreover, in recent years, the rise of deep learning technology has provided new ideas and methods for ATM cyber threat entity recognition. Alternatively, in the convolutional neural network (CNN), the convolution operation can efficiently extract the local features, while it is difficult to capture the global representation information. In Transformer, the attention mechanism can capture feature dependencies over long distances, while it usually ignores the details of local features. To solve these problems, a TextCNN-Flat-Lattice Transformer (TCFLTformer) with CNN-Transformer hybrid architecture is proposed for ATM cyber threat entity recognition, in which a relative positional embedding (RPE) is designed to encode position text content information, and a multibranch prediction head (MBPH) is utilized to enhance deep feature learning. TCFLTformer first uses CNN to carry out convolution and pooling operations on the text to extract local features and then uses a Flat-Lattice Transformer to learn temporal and relative positional characteristics of the text to obtain the final annotation results. Experimental results show that this method has achieved better results in the task of ATM cyber threat entity recognition, and it has high practical value and theoretical contribution. Besides, the proposed method expands the research field of ATM cyber threat entity recognition, and the research results can also provide references for other text classification and sequence annotation tasks.
50
Yu, Bing, Yan Huang, Guang Cheng, Dongjin Huang et Youdong Ding. « Graph U-Shaped Network with Mapping-Aware Local Enhancement for Single-Frame 3D Human Pose Estimation ». Electronics 12, no 19 (2 octobre 2023) : 4120. http://dx.doi.org/10.3390/electronics12194120.
Texte intégralRésumé :
The development of 2D-to-3D approaches for 3D monocular single-frame human pose estimation faces challenges related to noisy input and failure to capture long-range joint correlations, leading to unreasonable predictions. To this end, we propose a straightforward, but effective U-shaped network called the mapping-aware U-shaped graph convolutional network (M-UGCN) for single-frame applications. This network applies skeletal pooling/unpooling operations to expand the limited convolutional receptive field. For noisy inputs, as local nodes have direct access to the subtle discrepancies between poses, we define an additional mapping-aware local-enhancement mechanism to focus on local node interactions across multiple scales. We evaluated our proposed method on the benchmark datasets Human3.6M and MPI-INF-3DHP, and the experimental results demonstrated the robustness of the M-UGCN against noisy inputs. Notably, the average error in the proposed method was found to be 4.1% lower when compared to state-of-the-art methods adopting similar multi-scale learning approaches.