Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Graph Attention Networks.
Articles de revues sur le sujet « Graph Attention Networks »
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 Attention Networks ».
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
Wu, Nan, et Chaofan Wang. « Ensemble Graph Attention Networks ». Transactions on Machine Learning and Artificial Intelligence 10, no 3 (12 juin 2022) : 29–41. http://dx.doi.org/10.14738/tmlai.103.12399.
Texte intégralRésumé :
Graph neural networks have demonstrated its success in many applications on graph-structured data. Many efforts have been devoted to elaborating new network architectures and learning algorithms over the past decade. The exploration of applying ensemble learning techniques to enhance existing graph algorithms have been overlooked. In this work, we propose a simple generic bagging-based ensemble learning strategy which is applicable to any backbone graph models. We then propose two ensemble graph neural network models – Ensemble-GAT and Ensemble-HetGAT by applying the ensemble strategy to the graph attention network (GAT), and a heterogeneous graph attention network (HetGAT). We demonstrate the effectiveness of the proposed ensemble strategy on GAT and HetGAT through comprehensive experiments with four real-world homogeneous graph datasets and three real-world heterogeneous graph datasets on node classification tasks. The proposed Ensemble-GAT and Ensemble-HetGAT outperform the state-of-the-art graph neural network and heterogeneous graph neural network models on most of the benchmark datasets. The proposed ensemble strategy also alleviates the over-smoothing problem in GAT and HetGAT.
2
Murzin, M. V., I. A. Kulikov et N. A. Zhukova. « Methods for Constructing Graph Neural Networks ». LETI Transactions on Electrical Engineering & ; Computer Science 17, no 10 (2024) : 40–48. https://doi.org/10.32603/2071-8985-2024-17-10-40-48.
Texte intégralRésumé :
Discusses an approach to classifying graph neural networks in terms of basic concepts. In addition, the fundamentals of convolutional graph neural networks, Graph attentional neural networks, recurrent graph neural networks, graph automatic encoders, and spatial-temporal graph neural networks are discussed. On the example of Cora dataset, a comparison of neural network models presented in TensorFlow, PyTorch libraries, as well as the model of graph neural network of attention for the task of classification of nodes of the knowledge graph, is carried out. The efficiency of using graph attention networks to solve the problem of graph node classification is shown.
3
Sheng, Jinfang, Yufeng Zhang, Bin Wang et Yaoxing Chang. « MGATs : Motif-Based Graph Attention Networks ». Mathematics 12, no 2 (16 janvier 2024) : 293. http://dx.doi.org/10.3390/math12020293.
Texte intégralRésumé :
In recent years, graph convolutional neural networks (GCNs) have become a popular research topic due to their outstanding performance in various complex network data mining tasks. However, current research on graph neural networks lacks understanding of the high-order structural features of networks, focusing mostly on node features and first-order neighbor features. This article proposes two new models, MGAT and MGATv2, by introducing high-order structure motifs that frequently appear in networks and combining them with graph attention mechanisms. By introducing a mixed information matrix based on motifs, the generation process of graph attention coefficients is improved, allowing the model to capture higher-order structural features. Compared with the latest research on various graph neural networks, both MGAT and MGATv2 achieve good results in node classification tasks. Furthermore, through various experimental studies on real datasets, we demonstrate that the introduction of network structural motifs can effectively enhance the expressive power of graph neural networks, indicating that both high-order structural features and attribute features are important components of network feature learning.
4
Chatzianastasis, Michail, Johannes Lutzeyer, George Dasoulas et Michalis Vazirgiannis. « Graph Ordering Attention Networks ». Proceedings of the AAAI Conference on Artificial Intelligence 37, no 6 (26 juin 2023) : 7006–14. http://dx.doi.org/10.1609/aaai.v37i6.25856.
Texte intégralRésumé :
Graph Neural Networks (GNNs) have been successfully used in many problems involving graph-structured data, achieving state-of-the-art performance. GNNs typically employ a message-passing scheme, in which every node aggregates information from its neighbors using a permutation-invariant aggregation function. Standard well-examined choices such as the mean or sum aggregation functions have limited capabilities, as they are not able to capture interactions among neighbors. In this work, we formalize these interactions using an information-theoretic framework that notably includes synergistic information. Driven by this definition, we introduce the Graph Ordering Attention (GOAT) layer, a novel GNN component that captures interactions between nodes in a neighborhood. This is achieved by learning local node orderings via an attention mechanism and processing the ordered representations using a recurrent neural network aggregator. This design allows us to make use of a permutation-sensitive aggregator while maintaining the permutation-equivariance of the proposed GOAT layer. The GOAT model demonstrates its increased performance in modeling graph metrics that capture complex information, such as the betweenness centrality and the effective size of a node. In practical use-cases, its superior modeling capability is confirmed through its success in several real-world node classification benchmarks.
5
Li, Yu, Yuan Tian, Jiawei Zhang et Yi Chang. « Learning Signed Network Embedding via Graph Attention ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 04 (3 avril 2020) : 4772–79. http://dx.doi.org/10.1609/aaai.v34i04.5911.
Texte intégralRésumé :
Learning the low-dimensional representations of graphs (i.e., network embedding) plays a critical role in network analysis and facilitates many downstream tasks. Recently graph convolutional networks (GCNs) have revolutionized the field of network embedding, and led to state-of-the-art performance in network analysis tasks such as link prediction and node classification. Nevertheless, most of the existing GCN-based network embedding methods are proposed for unsigned networks. However, in the real world, some of the networks are signed, where the links are annotated with different polarities, e.g., positive vs. negative. Since negative links may have different properties from the positive ones and can also significantly affect the quality of network embedding. Thus in this paper, we propose a novel network embedding framework SNEA to learn Signed Network Embedding via graph Attention. In particular, we propose a masked self-attentional layer, which leverages self-attention mechanism to estimate the importance coefficient for pair of nodes connected by different type of links during the embedding aggregation process. Then SNEA utilizes the masked self-attentional layers to aggregate more important information from neighboring nodes to generate the node embeddings based on balance theory. Experimental results demonstrate the effectiveness of the proposed framework through signed link prediction task on several real-world signed network datasets.
6
Wang, Bin, Yu Chen, Jinfang Sheng et Zhengkun He. « Attributed Graph Embedding Based on Attention with Cluster ». Mathematics 10, no 23 (1 décembre 2022) : 4563. http://dx.doi.org/10.3390/math10234563.
Texte intégralRésumé :
Graph embedding is of great significance for the research and analysis of graphs. Graph embedding aims to map nodes in the network to low-dimensional vectors while preserving information in the original graph of nodes. In recent years, the appearance of graph neural networks has significantly improved the accuracy of graph embedding. However, the influence of clusters was not considered in existing graph neural network (GNN)-based methods, so this paper proposes a new method to incorporate the influence of clusters into the generation of graph embedding. We use the attention mechanism to pass the message of the cluster pooled result and integrate the whole process into the graph autoencoder as the third layer of the encoder. The experimental results show that our model has made great improvement over the baseline methods in the node clustering and link prediction tasks, demonstrating that the embeddings generated by our model have excellent expressiveness.
7
Li, Zitong, Xiang Cheng, Lixiao Sun, Ji Zhang et Bing Chen. « A Hierarchical Approach for Advanced Persistent Threat Detection with Attention-Based Graph Neural Networks ». Security and Communication Networks 2021 (4 mai 2021) : 1–14. http://dx.doi.org/10.1155/2021/9961342.
Texte intégralRésumé :
Advanced Persistent Threats (APTs) are the most sophisticated attacks for modern information systems. Currently, more and more researchers begin to focus on graph-based anomaly detection methods that leverage graph data to model normal behaviors and detect outliers for defending against APTs. However, previous studies of provenance graphs mainly concentrate on system calls, leading to difficulties in modeling network behaviors. Coarse-grained correlation graphs depend on handcrafted graph construction rules and, thus, cannot adequately explore log node attributes. Besides, the traditional Graph Neural Networks (GNNs) fail to consider meaningful edge features and are difficult to perform heterogeneous graphs embedding. To overcome the limitations of the existing approaches, we present a hierarchical approach for APT detection with novel attention-based GNNs. We propose a metapath aggregated GNN for provenance graph embedding and an edge enhanced GNN for host interactive graph embedding; thus, APT behaviors can be captured at both the system and network levels. A novel enhancement mechanism is also introduced to dynamically update the detection model in the hierarchical detection framework. Evaluations show that the proposed method outperforms the state-of-the-art baselines in APT detection.
8
Chen, Lu, Boer Lv, Chi Wang, Su Zhu, Bowen Tan et Kai Yu. « Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural Networks ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 05 (3 avril 2020) : 7521–28. http://dx.doi.org/10.1609/aaai.v34i05.6250.
Texte intégralRésumé :
Dialogue state tracking (DST) aims at estimating the current dialogue state given all the preceding conversation. For multi-domain DST, the data sparsity problem is also a major obstacle due to the increased number of state candidates. Existing approaches generally predict the value for each slot independently and do not consider slot relations, which may aggravate the data sparsity problem. In this paper, we propose a Schema-guided multi-domain dialogue State Tracker with graph attention networks (SST) that predicts dialogue states from dialogue utterances and schema graphs which contain slot relations in edges. We also introduce a graph attention matching network to fuse information from utterances and graphs, and a recurrent graph attention network to control state updating. Experiment results show that our approach obtains new state-of-the-art performance on both MultiWOZ 2.0 and MultiWOZ 2.1 benchmarks.
9
Liu, Jie, Lingyun Song, Li Gao et Xuequn Shang. « MMAN : Metapath Based Multi-Level Graph Attention Networks for Heterogeneous Network Embedding (Student Abstract) ». Proceedings of the AAAI Conference on Artificial Intelligence 36, no 11 (28 juin 2022) : 13005–6. http://dx.doi.org/10.1609/aaai.v36i11.21639.
Texte intégralRésumé :
Current Heterogeneous Network Embedding (HNE) models can be roughly divided into two types, i.e., relation-aware and metapath-aware models. However, they either fail to represent the non-pairwise relations in heterogeneous graph, or only capable of capturing local information around target node. In this paper, we propose a metapath based multilevel graph attention networks (MMAN) to jointly learn node embeddings on two substructures, i.e., metapath based graphs and hypergraphs extracted from original heterogeneous graph. Extensive experiments on three benchmark datasets for node classification and node clustering demonstrate the superiority of MMAN over the state-of-the-art works.
10
Wang, Rui, Bicheng Li, Shengwei Hu, Wenqian Du et Min Zhang. « Knowledge Graph Embedding via Graph Attenuated Attention Networks ». IEEE Access 8 (2020) : 5212–24. http://dx.doi.org/10.1109/access.2019.2963367.
Texte intégral
11
Wan, Qizhi, Changxuan Wan, Keli Xiao, Kun Lu, Chenliang Li, Xiping Liu et Dexi Liu. « Dependency Structure-Enhanced Graph Attention Networks for Event Detection ». Proceedings of the AAAI Conference on Artificial Intelligence 38, no 17 (24 mars 2024) : 19098–106. http://dx.doi.org/10.1609/aaai.v38i17.29877.
Texte intégralRésumé :
Existing models on event detection share three-fold limitations, including (1) insufficient consideration of the structures between dependency relations, (2) limited exploration of the directed-edge semantics, and (3) issues in strengthening the event core arguments. To tackle these problems, we propose a dependency structure-enhanced event detection framework. In addition to the traditional token dependency parsing tree, denoted as TDG, our model considers the dependency edges in it as new nodes and constructs a dependency relation graph (DRG). DRG allows the embedding representations of dependency relations to be updated as nodes rather than edges in a graph neural network. Moreover, the levels of core argument nodes in the two graphs are adjusted by dependency relation types in TDG to enhance their status. Subsequently, the two graphs are further encoded and jointly trained in graph attention networks (GAT). Importantly, we design an interaction strategy of node embedding for the two graphs and refine the attention coefficient computational method to encode the semantic meaning of directed edges. Extensive experiments are conducted to validate the effectiveness of our method, and the results confirm its superiority over the state-of-the-art baselines. Our model outperforms the best benchmark with the F1 score increased by 3.5 and 3.4 percentage points on ACE2005 English and Chinese corpus.
12
Gu, Yafeng, et Li Deng. « STAGCN : Spatial–Temporal Attention Graph Convolution Network for Traffic Forecasting ». Mathematics 10, no 9 (8 mai 2022) : 1599. http://dx.doi.org/10.3390/math10091599.
Texte intégralRésumé :
Traffic forecasting plays an important role in intelligent transportation systems. However, the prediction task is highly challenging due to the mixture of global and local spatiotemporal dependencies involved in traffic data. Existing graph neural networks (GNNs) typically capture spatial dependencies with the predefined or learnable static graph structure, ignoring the hidden dynamic patterns in traffic networks. Meanwhile, most recurrent neural networks (RNNs) or convolutional neural networks (CNNs) cannot effectively capture temporal correlations, especially for long-term temporal dependencies. In this paper, we propose a spatial–temporal attention graph convolution network (STAGCN), which acquires a static graph and a dynamic graph from data without any prior knowledge. The static graph aims to model global space adaptability, and the dynamic graph is designed to capture local dynamics in the traffic network. A gated temporal attention module is further introduced for long-term temporal dependencies, where a causal-trend attention mechanism is proposed to increase the awareness of causality and local trends in time series. Extensive experiments on four real-world traffic flow datasets demonstrate that STAGCN achieves an outstanding prediction accuracy improvement over existing solutions.
13
Wang, Han, et Deok-Hwan Kim. « Graph Neural Network-Based Speech Emotion Recognition : A Fusion of Skip Graph Convolutional Networks and Graph Attention Networks ». Electronics 13, no 21 (27 octobre 2024) : 4208. http://dx.doi.org/10.3390/electronics13214208.
Texte intégralRésumé :
In speech emotion recognition (SER), our research addresses the critical challenges of capturing and evaluating node information and their complex interrelationships within speech data. We introduce Skip Graph Convolutional and Graph Attention Network (SkipGCNGAT), an innovative model that combines the strengths of skip graph convolutional networks (SkipGCNs) and graph attention networks (GATs) to address these challenges. SkipGCN incorporates skip connections, enhancing the flow of information across the network and mitigating issues such as vanishing gradients, while also facilitating deeper representation learning. Meanwhile, the GAT in the model assigns dynamic attention weights to neighboring nodes, allowing SkipGCNGAT to focus on both the most relevant local and global interactions within the speech data. This enables the model to capture subtle and complex dependencies between speech segments, thus facilitating a more accurate interpretation of emotional content. It overcomes the limitations of previous single-layer graph models, which were unable to effectively represent these intricate relationships across time and in different speech contexts. Additionally, by introducing a pre-pooling SkipGCN combination technique, we further enhance the ability of the model to integrate multi-layer information before pooling, improving its capacity to capture both spatial and temporal features in speech. Furthermore, we rigorously evaluated SkipGCNGAT on the IEMOCAP and MSP-IMPROV datasets, two benchmark datasets in SER. The results demonstrated that SkipGCNGAT consistently achieved state-of-the-art performance. These findings highlight the effectiveness of the proposed model in accurately recognizing emotions in speech, offering valuable insights and a solid foundation for future research on capturing complex relationships within speech signals for emotion recognition.
14
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.
15
Shang, Bin, Yinliang Zhao, Jun Liu et Di Wang. « Mixed Geometry Message and Trainable Convolutional Attention Network for Knowledge Graph Completion ». Proceedings of the AAAI Conference on Artificial Intelligence 38, no 8 (24 mars 2024) : 8966–74. http://dx.doi.org/10.1609/aaai.v38i8.28745.
Texte intégralRésumé :
Knowledge graph completion (KGC) aims to study the embedding representation to solve the incompleteness of knowledge graphs (KGs). Recently, graph convolutional networks (GCNs) and graph attention networks (GATs) have been widely used in KGC tasks by capturing neighbor information of entities. However, Both GCNs and GATs based KGC models have their limitations, and the best method is to analyze the neighbors of each entity (pre-validating), while this process is prohibitively expensive. Furthermore, the representation quality of the embeddings can affect the aggregation of neighbor information (message passing). To address the above limitations, we propose a novel knowledge graph completion model with mixed geometry message and trainable convolutional attention network named MGTCA. Concretely, the mixed geometry message function generates rich neighbor message by integrating spatially information in the hyperbolic space, hypersphere space and Euclidean space jointly. To complete the autonomous switching of graph neural networks (GNNs) and eliminate the necessity of pre-validating the local structure of KGs, a trainable convolutional attention network is proposed by comprising three types of GNNs in one trainable formulation. Furthermore, a mixed geometry scoring function is proposed, which calculates scores of triples by novel prediction function and similarity function based on different geometric spaces. Extensive experiments on three standard datasets confirm the effectiveness of our innovations, and the performance of MGTCA is significantly improved compared to the state-of-the-art approaches.
16
Long, Yahui, Min Wu, Yong Liu, Chee Keong Kwoh, Jiawei Luo et Xiaoli Li. « Ensembling graph attention networks for human microbe–drug association prediction ». Bioinformatics 36, Supplement_2 (décembre 2020) : i779—i786. http://dx.doi.org/10.1093/bioinformatics/btaa891.
Texte intégralRésumé :
Abstract Motivation Human microbes get closely involved in an extensive variety of complex human diseases and become new drug targets. In silico methods for identifying potential microbe–drug associations provide an effective complement to conventional experimental methods, which can not only benefit screening candidate compounds for drug development but also facilitate novel knowledge discovery for understanding microbe–drug interaction mechanisms. On the other hand, the recent increased availability of accumulated biomedical data for microbes and drugs provides a great opportunity for a machine learning approach to predict microbe–drug associations. We are thus highly motivated to integrate these data sources to improve prediction accuracy. In addition, it is extremely challenging to predict interactions for new drugs or new microbes, which have no existing microbe–drug associations. Results In this work, we leverage various sources of biomedical information and construct multiple networks (graphs) for microbes and drugs. Then, we develop a novel ensemble framework of graph attention networks with a hierarchical attention mechanism for microbe–drug association prediction from the constructed multiple microbe–drug graphs, denoted as EGATMDA. In particular, for each input graph, we design a graph convolutional network with node-level attention to learn embeddings for nodes (i.e. microbes and drugs). To effectively aggregate node embeddings from multiple input graphs, we implement graph-level attention to learn the importance of different input graphs. Experimental results under different cross-validation settings (e.g. the setting for predicting associations for new drugs) showed that our proposed method outperformed seven state-of-the-art methods. Case studies on predicted microbe–drug associations further demonstrated the effectiveness of our proposed EGATMDA method. Availability Source codes and supplementary materials are available at: https://github.com/longyahui/EGATMDA/ Supplementary information Supplementary data are available at Bioinformatics online.
17
Hsu, Howard Muchen, Zai-Fu Yao, Kai Hwang et Shulan Hsieh. « Between-module functional connectivity of the salient ventral attention network and dorsal attention network is associated with motor inhibition ». PLOS ONE 15, no 12 (3 décembre 2020) : e0242985. http://dx.doi.org/10.1371/journal.pone.0242985.
Texte intégralRésumé :
The ability to inhibit motor response is crucial for daily activities. However, whether brain networks connecting spatially distinct brain regions can explain individual differences in motor inhibition is not known. Therefore, we took a graph-theoretic perspective to examine the relationship between the properties of topological organization in functional brain networks and motor inhibition. We analyzed data from 141 healthy adults aged 20 to 78, who underwent resting-state functional magnetic resonance imaging and performed a stop-signal task along with neuropsychological assessments outside the scanner. The graph-theoretic properties of 17 functional brain networks were estimated, including within-network connectivity and between-network connectivity. We employed multiple linear regression to examine how these graph-theoretical properties were associated with motor inhibition. The results showed that between-network connectivity of the salient ventral attention network and dorsal attention network explained the highest and second highest variance of individual differences in motor inhibition. In addition, we also found those two networks span over brain regions in the frontal-cingulate-parietal network, suggesting that these network interactions are also important to motor inhibition.
18
Nikolentzos, Giannis, Antoine Tixier et Michalis Vazirgiannis. « Message Passing Attention Networks for Document Understanding ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 05 (3 avril 2020) : 8544–51. http://dx.doi.org/10.1609/aaai.v34i05.6376.
Texte intégralRésumé :
Graph neural networks have recently emerged as a very effective framework for processing graph-structured data. These models have achieved state-of-the-art performance in many tasks. Most graph neural networks can be described in terms of message passing, vertex update, and readout functions. In this paper, we represent documents as word co-occurrence networks and propose an application of the message passing framework to NLP, the Message Passing Attention network for Document understanding (MPAD). We also propose several hierarchical variants of MPAD. Experiments conducted on 10 standard text classification datasets show that our architectures are competitive with the state-of-the-art. Ablation studies reveal further insights about the impact of the different components on performance. Code is publicly available at: https://github.com/giannisnik/mpad.
19
Wang, Wanru, Yuwei Lv, Yonggang Wen et Xuemei Sun. « Rumor Detection Based on Knowledge Enhancement and Graph Attention Network ». Discrete Dynamics in Nature and Society 2022 (6 octobre 2022) : 1–12. http://dx.doi.org/10.1155/2022/6257658.
Texte intégralRésumé :
Presently, most of the existing rumor detection methods focus on learning and integrating various features for detection, but due to the complexity of the language, these models often rarely consider the relationship between the parts of speech. For the first time, this paper integrated a knowledge graphs and graph attention networks to solve this problem through attention mechanisms. A knowledge graphs can be the most effective and intuitive expression of relationships between entities, providing problem analysis from the perspective of “relationships”. This paper used knowledge graphs to enhance topics and learn the text features by using self-attention. Furthermore, this paper defined a common dependent tree structure, and then the ordinary dependency trees were reshaped to make it generate a motif-dependent tree. A graph attention network was adopted to collect feature representations derived from the corresponding syntax-dependent tree production. The attention mechanism was an allocation mechanism of weight parameters that could help the model capture important information. Rumors were then detected accordingly by using the attention mechanism to combine text representations learned from self-attention and graph representations learned from the graph attention network. Finally, numerous experiments were performed on the standard dataset Twitter, and the proposed model here had achieved a 7.7% improved accuracy rate compared with the benchmark model.
20
Han, Wenhao, Xuemei Liu, Jianhao Zhang et Hairui Li. « Hierarchical Perceptual Graph Attention Network for Knowledge Graph Completion ». Electronics 13, no 4 (9 février 2024) : 721. http://dx.doi.org/10.3390/electronics13040721.
Texte intégralRésumé :
Knowledge graph completion (KGC), the process of predicting missing knowledge through known triples, is a primary focus of research in the field of knowledge graphs. As an important graph representation technique in deep learning, graph neural networks (GNNs) perform well in knowledge graph completion, but most existing graph neural network-based knowledge graph completion methods tend to aggregate neighborhood information directly and individually, ignoring the rich hierarchical semantic structure of KGs. As a result, how to effectively deal with multi-level complex relations is still not well resolved. In this study, we present a hierarchical knowledge graph completion technique that combines both relation-level and entity-level attention and incorporates a weight matrix to enhance the significance of the embedded information under different semantic conditions. Furthermore, it updates neighborhood information to the central entity using a hierarchical aggregation approach. The proposed model enhances the capacity to capture hierarchical semantic feature information and is adaptable to various scoring functions as decoders, thus yielding robust results. We conducted experiments on a public benchmark dataset and compared it with several state-of-the-art models, and the experimental results indicate that our proposed model outperforms existing models in several aspects, proving its superior performance and validating the effectiveness of the model.
21
Mardani, Konstantina, Nicholas Vretos et Petros Daras. « Mahalanobis Distance-Based Graph Attention Networks ». IEEE Access 12 (2024) : 166923–35. http://dx.doi.org/10.1109/access.2024.3495531.
Texte intégral
22
Xie, Yu, Yuanqiao Zhang, Maoguo Gong, Zedong Tang et Chao Han. « MGAT : Multi-view Graph Attention Networks ». Neural Networks 132 (décembre 2020) : 180–89. http://dx.doi.org/10.1016/j.neunet.2020.08.021.
Texte intégral
23
Han, Xiaotian, Kaixiong Zhou, Ting-Hsiang Wang, Jundong Li, Fei Wang et Na Zou. « Marginal Nodes Matter : Towards Structure Fairness in Graphs ». ACM SIGKDD Explorations Newsletter 25, no 2 (26 mars 2024) : 4–13. http://dx.doi.org/10.1145/3655103.3655105.
Texte intégralRésumé :
In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protecting sensitive attributes (e.g., age and gender), the fairness incurred by the graph structure should also be given attention. On the other hand, the information aggregation mechanism of graph neural networks amplifies such structure unfairness, as marginal nodes are often far away from other nodes. In this paper, we focus on novel fairness incurred by the graph structure on graph neural networks, named structure fairness. Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks. Motivated by the observation, we propose Structural Fair Graph Neural Network (SFairGNN), which combines neighborhood expansion based structure debiasing with hop-aware attentive information aggregation to achieve structure fairness. Our experiments show SFairGNN can significantly improve structure fairness while maintaining overall performance in the downstream tasks.
24
Wang, Ruiheng, Hongliang Zhu, Lu Wang, Zhaoyun Chen, Mingcheng Gao et Yang Xin. « User Identity Linkage Across Social Networks by Heterogeneous Graph Attention Network Modeling ». Applied Sciences 10, no 16 (7 août 2020) : 5478. http://dx.doi.org/10.3390/app10165478.
Texte intégralRésumé :
Today, social networks are becoming increasingly popular and indispensable, where users usually have multiple accounts. It is of considerable significance to conduct user identity linkage across social networks. We can comprehensively depict diversified characteristics of user behaviors, accurately model user profiles, conduct recommendations across social networks, and track cross social network user behaviors by user identity linkage. Existing works mainly focus on a specific type of user profile, user-generated content, and structural information. They have problems of weak data expression ability and ignored potential relationships, resulting in unsatisfactory performances of user identity linkage. Recently, graph neural networks have achieved excellent results in graph embedding, graph representation, and graph classification. As a graph has strong relationship expression ability, we propose a user identity linkage method based on a heterogeneous graph attention network mechanism (UIL-HGAN). Firstly, we represent user profiles, user-generated content, structural information, and their features in a heterogeneous graph. Secondly, we use multiple attention layers to aggregate user information. Finally, we use a multi-layer perceptron to predict user identity linkage. We conduct experiments on two real-world datasets: OSCHINA-Gitee and Facebook-Twitter. The results validate the effectiveness and advancement of UIL-HGAN by comparing different feature combinations and methods.
25
Catal, Cagatay, Hakan Gunduz et Alper Ozcan. « Malware Detection Based on Graph Attention Networks for Intelligent Transportation Systems ». Electronics 10, no 20 (18 octobre 2021) : 2534. http://dx.doi.org/10.3390/electronics10202534.
Texte intégralRésumé :
Intelligent Transportation Systems (ITS) aim to make transportation smarter, safer, reliable, and environmentally friendly without detrimentally affecting the service quality. ITS can face security issues due to their complex, dynamic, and non-linear properties. One of the most critical security problems is attacks that damage the infrastructure of the entire ITS. Attackers can inject malware code that triggers dangerous actions such as information theft and unwanted system moves. The main objective of this study is to improve the performance of malware detection models using Graph Attention Networks. To detect malware attacks addressing ITS, a Graph Attention Network (GAN)-based framework is proposed in this study. The inputs to this framework are the Application Programming Interface (API)-call graphs obtained from malware and benign Android apk files. During the graph creation, network metrics and the Node2Vec model are utilized to generate the node features. A GAN-based model is combined with different types of node features during the experiments and the performance is compared against Graph Convolutional Network (GCN). Experimental results demonstrated that the integration of the GAN and Node2Vec models provides the best performance in terms of F-measure and accuracy parameters and, also, the use of an attention mechanism in GAN improves the performance. Furthermore, node features generated with Node2Vec resulted in a 3% increase in classification accuracy compared to the features generated with network metrics.
26
Bae, Ji-Hun, Gwang-Hyun Yu, Ju-Hwan Lee, Dang Thanh Vu, Le Hoang Anh, Hyoung-Gook Kim et Jin-Young Kim. « Superpixel Image Classification with Graph Convolutional Neural Networks Based on Learnable Positional Embedding ». Applied Sciences 12, no 18 (13 septembre 2022) : 9176. http://dx.doi.org/10.3390/app12189176.
Texte intégralRésumé :
Graph convolutional neural networks (GCNNs) have been successfully applied to a wide range of problems, including low-dimensional Euclidean structural domains representing images, videos, and speech and high-dimensional non-Euclidean domains, such as social networks and chemical molecular structures. However, in computer vision, the existing GCNNs are not provided with positional information to distinguish between graphs of new structures; therefore, the performance of the image classification domain represented by arbitrary graphs is significantly poor. In this work, we introduce how to initialize the positional information through a random walk algorithm and continuously learn the additional position-embedded information of various graph structures represented over the superpixel images we choose for efficiency. We call this method the graph convolutional network with learnable positional embedding applied on images (IMGCN-LPE). We apply IMGCN-LPE to three graph convolutional models (the Chebyshev graph convolutional network, graph convolutional network, and graph attention network) to validate performance on various benchmark image datasets. As a result, although not as impressive as convolutional neural networks, the proposed method outperforms various other conventional convolutional methods and demonstrates its effectiveness among the same tasks in the field of GCNNs.
27
Cui, Wanqiu, Junping Du, Dawei Wang, Feifei Kou et Zhe Xue. « MVGAN : Multi-View Graph Attention Network for Social Event Detection ». ACM Transactions on Intelligent Systems and Technology 12, no 3 (19 juillet 2021) : 1–24. http://dx.doi.org/10.1145/3447270.
Texte intégralRésumé :
Social networks are critical sources for event detection thanks to the characteristics of publicity and dissemination. Unfortunately, the randomness and semantic sparsity of the social network text bring significant challenges to the event detection task. In addition to text, time is another vital element in reflecting events since events are often followed for a while. Therefore, in this article, we propose a novel method named Multi-View Graph Attention Network (MVGAN) for event detection in social networks. It enriches event semantics through both neighbor aggregation and multi-view fusion in a heterogeneous social event graph. Specifically, we first construct a heterogeneous graph by adding the hashtag to associate the isolated short texts and describe events comprehensively. Then, we learn view-specific representations of events through graph convolutional networks from the perspectives of text semantics and time distribution, respectively. Finally, we design a hashtag-based multi-view graph attention mechanism to capture the intrinsic interaction across different views and integrate the feature representations to discover events. Extensive experiments on public benchmark datasets demonstrate that MVGAN performs favorably against many state-of-the-art social network event detection algorithms. It also proves that more meaningful signals can contribute to improving the event detection effect in social networks, such as published time and hashtags.
28
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.
29
Guo, Ruiqiang, Juan Zou, Qianqian Bai, Wei Wang et Xiaomeng Chang. « Community Detection Fusing Graph Attention Network ». Mathematics 10, no 21 (7 novembre 2022) : 4155. http://dx.doi.org/10.3390/math10214155.
Texte intégralRésumé :
It has become a tendency to use a combination of autoencoders and graph neural networks for attribute graph clustering to solve the community detection problem. However, the existing methods do not consider the influence differences between node neighborhood information and high-order neighborhood information, and the fusion of structural and attribute features is insufficient. In order to make better use of structural information and attribute information, we propose a model named community detection fusing graph attention network (CDFG). Specifically, we firstly use an autoencoder to learn attribute features. Then the graph attention network not only calculates the influence weight of the neighborhood node on the target node but also adds the high-order neighborhood information to learn the structural features. After that, the two features are initially fused by the balance parameter. The feature fusion module extracts the hidden layer representation of the graph attention layer to calculate the self-correlation matrix, which is multiplied by the node representation obtained by the preliminary fusion to achieve secondary fusion. Finally, the self-supervision mechanism makes it face the community detection task. Experiments are conducted on six real datasets. Using four evaluation metrics, the CDFG model performs better on most datasets, especially for the networks with longer average paths and diameters and smaller clustering coefficients.
30
Cai, Zengyu, Chunchen Tan, Jianwei Zhang, Liang Zhu et Yuan Feng. « DBSTGNN-Att : Dual Branch Spatio-Temporal Graph Neural Network with an Attention Mechanism for Cellular Network Traffic Prediction ». Applied Sciences 14, no 5 (5 mars 2024) : 2173. http://dx.doi.org/10.3390/app14052173.
Texte intégralRésumé :
As network technology continues to develop, the popularity of various intelligent terminals has accelerated, leading to a rapid growth in the scale of wireless network traffic. This growth has resulted in significant pressure on resource consumption and network security maintenance. The objective of this paper is to enhance the prediction accuracy of cellular network traffic in order to provide reliable support for the subsequent base station sleep control or the identification of malicious traffic. To achieve this target, a cellular network traffic prediction method based on multi-modal data feature fusion is proposed. Firstly, an attributed K-nearest node (KNN) graph is constructed based on the similarity of data features, and the fused high-dimensional features are incorporated into the graph to provide more information for the model. Subsequently, a dual branch spatio-temporal graph neural network with an attention mechanism (DBSTGNN-Att) is designed for cellular network traffic prediction. Extensive experiments conducted on real-world datasets demonstrate that the proposed method outperforms baseline models, such as temporal graph convolutional networks (T-GCNs) and spatial–temporal self-attention graph convolutional networks (STA-GCNs) with lower mean absolute error (MAE) values of 6.94% and 2.11%, respectively. Additionally, the ablation experimental results show that the MAE of multi-modal feature fusion using the attributed KNN graph is 8.54% lower compared to that of the traditional undirected graphs.
31
Zhang, Guoxing, Haixiao Wang et Yuanpu Yin. « Multi-type Parameter Prediction of Traffic Flow Based on Time-space Attention Graph Convolutional Network ». International Journal of Circuits, Systems and Signal Processing 15 (11 août 2021) : 902–12. http://dx.doi.org/10.46300/9106.2021.15.97.
Texte intégralRésumé :
Graph Convolutional Neural Networks are more and more widely used in traffic flow parameter prediction tasks by virtue of their excellent non-Euclidean spatial feature extraction capabilities. However, most graph convolutional neural networks are only used to predict one type of traffic flow parameter. This means that the proposed graph convolutional neural network may only be effective for specific parameters of specific travel modes. In order to improve the universality of graph convolutional neural networks. By embedding time feature and spatio-temporal attention layer, we propose a spatio-temporal attention graph convolutional neural network based on the attention mechanism of the neural network. Through experiments on passenger flow data and vehicle speed data of two different travel modes (Hangzhou Metro Data and California Highway Data), it is verified that the proposed spatio-temporal attention graph convolutional neural network can be used to predict passenger flow and vehicle speed simultaneously. Meanwhile, the error distribution range of the proposed model is minimum, and the overall level of prediction results is more accurate.
32
Lai, Qinghan, Zihan Zhou et Song Liu. « Joint Entity-Relation Extraction via Improved Graph Attention Networks ». Symmetry 12, no 10 (21 octobre 2020) : 1746. http://dx.doi.org/10.3390/sym12101746.
Texte intégralRésumé :
Joint named entity recognition and relation extraction is an essential natural language processing task that aims to identify entities and extract the corresponding relations in an end-to-end manner. At present, compared with the named entity recognition task, the relation extraction task performs poorly on complex text. To solve this problem, we proposed a novel joint model named extracting Entity-Relations viaImproved Graph Attention networks (ERIGAT), which enhances the ability of the relation extraction task. In our proposed model, we introduced the graph attention network to extract entities and relations after graph embedding based on constructing symmetry relations. To mitigate the over-smoothing problem of graph convolutional networks, inspired by matrix factorization, we improved the graph attention network by designing a new multi-head attention mechanism and sharing attention parameters. To enhance the model robustness, we adopted the adversarial training to generate adversarial samples for training by adding tiny perturbations. Comparing with typical baseline models, we comprehensively evaluated our model by conducting experiments on an open domain dataset (CoNLL04) and a medical domain dataset (ADE). The experimental results demonstrate the effectiveness of ERIGAT in extracting entity and relation information.
33
Wu, Zheng, Hongchang Chen, Jianpeng Zhang, Yulong Pei et Zishuo Huang. « Temporal motif-based attentional graph convolutional network for dynamic link prediction ». Intelligent Data Analysis 27, no 1 (30 janvier 2023) : 241–68. http://dx.doi.org/10.3233/ida-216169.
Texte intégralRésumé :
Dynamic link prediction is an important component of the dynamic network analysis with many real-world applications. Currently, most advancements focus on analyzing link-defined neighborhoods with graph convolutional networks (GCN), while ignoring the influence of higher-order structural and temporal interacting features on link formation. Therefore, based on recent progress in modeling temporal graphs, we propose a novel temporal motif-based attentional graph convolutional network model (TMAGCN) for dynamic link prediction. As dynamic graphs usually contain periodical patterns, we first propose a temporal motif matrix construction method to capture higher-order structural and temporal features, then introduce a spatial convolution operation following a temporal motif-attention mechanism to encode these features into node embeddings. Furthermore, we design two methods to combine multiple temporal motif-based attentions, a dynamic attention-based method and a reinforcement learning-based method, to allow each individual node to make the most of the relevant motif-based neighborhood to propagate and aggregate information in the graph convolutional layers. Experimental results on various real-world datasets demonstrate that the proposed model is superior to state-of-the-art baselines on the dynamic link prediction task. It also reveals that temporal motif can manifest the essential dynamic mechanism of the network.
34
Chen, Yong, Xiao-Zhu Xie, Wei Weng et Yi-Fan He. « Multi-Order-Content-Based Adaptive Graph Attention Network for Graph Node Classification ». Symmetry 15, no 5 (7 mai 2023) : 1036. http://dx.doi.org/10.3390/sym15051036.
Texte intégralRésumé :
In graph-structured data, the node content contains rich information. Therefore, how to effectively utilize the content is crucial to improve the performance of graph convolutional networks (GCNs) on various analytical tasks. However, current GCNs do not fully utilize the content, especially multi-order content. For example, graph attention networks (GATs) only focus on low-order content, while high-order content is completely ignored. To address this issue, we propose a novel graph attention network with adaptability that could fully utilize the features of multi-order content. Its core idea has the following novelties: First, we constructed a high-order content attention mechanism that could focus on high-order content to evaluate attention weights. Second, we propose a multi-order content attention mechanism that can fully utilize multi-order content, i.e., it combines the attention mechanisms of high- and low-order content. Furthermore, the mechanism has adaptability, i.e., it can perform a good trade-off between high- and low-order content according to the task requirements. Lastly, we applied this mechanism to constructing a graph attention network with structural symmetry. This mechanism could more reasonably evaluate the attention weights between nodes, thereby improving the convergence of the network. In addition, we conducted experiments on multiple datasets and compared the proposed model with state-of-the-art models in multiple dimensions. The results validate the feasibility and effectiveness of the proposed model.
35
Lu, Zhilong, Weifeng Lv, Zhipu Xie, Bowen Du, Guixi Xiong, Leilei Sun et Haiquan Wang. « Graph Sequence Neural Network with an Attention Mechanism for Traffic Speed Prediction ». ACM Transactions on Intelligent Systems and Technology 13, no 2 (30 avril 2022) : 1–24. http://dx.doi.org/10.1145/3470889.
Texte intégralRésumé :
Recent years have witnessed the emerging success of Graph Neural Networks (GNNs) for modeling graphical data. A GNN can model the spatial dependencies of nodes in a graph based on message passing through node aggregation. However, in many application scenarios, these spatial dependencies can change over time, and a basic GNN model cannot capture these changes. In this article, we propose a G raph S eq uence neural network with an A tt ention mechanism (GSeqAtt) for processing graph sequences. More specifically, two attention mechanisms are combined: a horizontal mechanism and a vertical mechanism. GTransformer, which is a horizontal attention mechanism for handling time series, is used to capture the correlations between graphs in the input time sequence. The vertical attention mechanism, a Graph Network (GN) block structure with an attention mechanism (GNAtt), acts within the graph structure in each frame of the time series. Experiments show that our proposed model is able to handle information propagation for graph sequences accurately and efficiently. Moreover, results on real-world data from three road intersections show that our GSeqAtt outperforms state-of-the-art baselines on the traffic speed prediction task.
36
Chang, Ze, Yunfei Cai, Xiao Fan Liu, Zhenping Xie, Yuan Liu et Qianyi Zhan. « Anomalous Node Detection in Blockchain Networks Based on Graph Neural Networks ». Sensors 25, no 1 (24 décembre 2024) : 1. https://doi.org/10.3390/s25010001.
Texte intégralRésumé :
With the rapid development of blockchain technology, fraudulent activities have significantly increased, posing a major threat to the personal assets of blockchain users. The blockchain transaction network formed during user transactions can be represented as a graph consisting of nodes and edges, making it suitable for a graph data structure. Fraudulent nodes in the transaction network are referred to as anomalous nodes. In recent years, the mainstream method for detecting anomalous nodes in graphs has been the use of graph data mining techniques. However, anomalous nodes typically constitute only a small portion of the transaction network, known as the minority class, while the majority of nodes are normal nodes, referred to as the majority class. This discrepancy in sample sizes results in class imbalance data, where models tend to overfit the features of the majority class and neglect those of the minority class. This issue presents significant challenges for traditional graph data mining techniques. In this paper, we propose a novel graph neural network method to overcome class imbalance issues by improving the Graph Attention Network (GAT) and incorporating ensemble learning concepts. Our method combines GAT with a subtree attention mechanism and two ensemble learning methods: Bootstrap Aggregating (Bagging) and Categorical Boosting (CAT), called SGAT-BC. We conducted experiments on four real-world blockchain transaction datasets, and the results demonstrate that SGAT-BC outperforms existing baseline models.
37
Liao, Guoqiong, et Xiaobin Deng. « Leveraging Social Relationship-Based Graph Attention Model for Group Event Recommendation ». Wireless Communications and Mobile Computing 2020 (29 octobre 2020) : 1–14. http://dx.doi.org/10.1155/2020/8834450.
Texte intégralRésumé :
Recently, event-based social networks(EBSN) such as Meetup, Plancast, and Douban have become popular. As users in the networks usually take groups as an unit to participate in events, it is necessary and meaningful to study effective strategies for recommending events to groups. Existing research on group event recommendation either has the problems of data sparse and cold start due to without considering of social relationships in the networks or makes the assumption that the influence weights between any pair of nodes in the user social graph are equal. In this paper, inspired by the graph neural network and attention mechanism, we propose a novel recommendation model named leveraging social relationship-based graph attention model (SRGAM) for group event recommendation. Specifically, we not only construct a user-event interaction graph and an event-user interaction graph, but also build a user-user social graph and an event-event social graph, to alleviate the problems of data sparse and cold start. In addition, by using a graph attention neural network to learn graph data, we can calculate the influence weight of each node in the graph, thereby generating more reasonable user latent vectors and event latent vectors. Furthermore, we use an attention mechanism to fuse multiple user vectors in a group, so as to generate a high-level group latent vector for rating prediction. Extensive experiments on real-world Meetup datasets demonstrate the effectiveness of the proposed model.
38
Shi, Jianrun, Leiyang Cui, Bo Gu, Bin Lyu et Shimin Gong. « State Transition Graph-Based Spatial–Temporal Attention Network for Cell-Level Mobile Traffic Prediction ». Sensors 23, no 23 (21 novembre 2023) : 9308. http://dx.doi.org/10.3390/s23239308.
Texte intégralRésumé :
Mobile traffic prediction enables the efficient utilization of network resources and enhances user experience. In this paper, we propose a state transition graph-based spatial–temporal attention network (STG-STAN) for cell-level mobile traffic prediction, which is designed to exploit the underlying spatial–temporal dynamic information hidden in the historical mobile traffic data. Specifically, we first identify the semantic context information over different segments of the historical data by constructing the state transition graphs, which may reveal different patterns of random fluctuation. Then, based on the state transition graphs, a spatial attention extraction module using graph convolutional networks (GCNs) is designed to aggregate the spatial information of different nodes in the state transition graph. Moreover, a temporal extraction module is employed to capture the dynamic evolution and temporal correlation of the state transition graphs over time. Such a spatial–temporal attention network can be further integrated with a parallel long short-term memory (LSTM) module to improve the accuracy of mobile traffic prediction. Extensive experiments demonstrate that the STG-STAN can better exploit the spatial–temporal information hidden in the state transition graphs, achieving superior performance compared with several baselines.
39
Zhang, Tianjiao, Xingjie Zhao, Hao Sun, Bo Gao et Xiaoqi Liu. « GATv2EPI : Predicting Enhancer–Promoter Interactions with a Dynamic Graph Attention Network ». Genes 15, no 12 (25 novembre 2024) : 1511. http://dx.doi.org/10.3390/genes15121511.
Texte intégralRésumé :
Background: The enhancer–promoter interaction (EPI) is a critical component of gene regulatory networks, playing a significant role in understanding the complexity of gene expression. Traditional EPI prediction methods focus on one-to-one interactions, neglecting more complex one-to-many and many-to-many patterns. To address this gap, we utilize graph neural networks to comprehensively explore all interaction patterns between enhancers and promoters, capturing complex regulatory relationships for more accurate predictions. Methods: In this study, we introduce a novel EPI prediction framework, GATv2EPI, based on dynamic graph attention neural networks. GATv2EPI leverages epigenetic information from enhancers, promoters, and their surrounding regions and organizes interactions into a network to comprehensively explore complex EPI regulatory patterns, including one-to-one, one-to-many, and many-to-many relationships. To avoid overfitting and ensure diverse data representation, we implemented a connectivity-based sampling method for dataset partitioning, which constructs graphs for each chromosome and assigns entire connected subgraphs to training or test sets, thereby preventing information leakage and ensuring comprehensive chromosomal representation. Results: In experiments conducted on four cell lines—NHEK, IMR90, HMEC, and K562—GATv2EPI demonstrated superior EPI recognition accuracy compared to existing similar methods, with a training time improvement of 95.29% over TransEPI. Conclusions: GATv2EPI enhances EPI prediction accuracy by capturing complex topological structure information from gene regulatory networks through graph neural networks. Additionally, our results emphasize the importance of epigenetic features surrounding enhancers and promoters in EPI prediction.
40
Van Trung, LAI, et NGUYEN Thi Thanh Giang. « NETWORK COMMUNITY DETECTION BASED ON THE ANGLE BETWEEN TWO VECTORS ». Vinh University Journal of Science 53, no 1A (20 mars 2023) : 95–105. http://dx.doi.org/10.56824/vujs.2023a162.
Texte intégralRésumé :
Recently, the problem of community detection has attracted the attention of many scientists. Most types of networks such as computer networks, biological networks and social networks, have a community structure. Community detection helps to understand the structure and properties of that real network. There have been many algorithms with different approaches, including coordinating vertices and building appropriate distances between them. In this paper, a random walk has been used to coordinate the vertices of the graph and use the cosine of the angle between two vectors to detect network communities. The article also presents the Modularity function to evaluate graph clustering. Some experimental results on randomly generated graphs and graphs generated from the real data set Zachary's karate club network have been presented and compared with the K-means++ algorithm.
41
Zhao, Jianan, Xiao Wang, Chuan Shi, Binbin Hu, Guojie Song et Yanfang Ye. « Heterogeneous Graph Structure Learning for Graph Neural Networks ». Proceedings of the AAAI Conference on Artificial Intelligence 35, no 5 (18 mai 2021) : 4697–705. http://dx.doi.org/10.1609/aaai.v35i5.16600.
Texte intégralRésumé :
Heterogeneous Graph Neural Networks (HGNNs) have drawn increasing attention in recent years and achieved outstanding performance in many tasks. The success of the existing HGNNs relies on one fundamental assumption, i.e., the original heterogeneous graph structure is reliable. However, this assumption is usually unrealistic, since the heterogeneous graph in reality is inevitably noisy or incomplete. Therefore, it is vital to learn the heterogeneous graph structure for HGNNs rather than rely only on the raw graph structure. In light of this, we make the first attempt towards learning an optimal heterogeneous graph structure for HGNNs and propose a novel framework HGSL, which jointly performs Heterogeneous Graph Structure Learning and GNN parameters learning for classification task. Different from traditional GSL on homogeneous graph, considering the heterogeneity of different relations in heterogeneous graph, HGSL generates each relation subgraph independently. Specifically, in each generated relation subgraph, HGSL not only considers the feature similarity by generating feature similarity graph, but also considers the complex heterogeneous interactions in features and semantics by generating feature propagation graph and semantic graph. Then, these graphs are fused to a learned heterogeneous graph and optimized together with a GNN towards classification objective. Extensive experiments on real-world graphs demonstrate that the proposed framework significantly outperforms the state-of-the-art methods.
42
Xia, Zhongxiu, Weiyu Zhang et Ziqiang Weng. « Social Recommendation System Based on Hypergraph Attention Network ». Computational Intelligence and Neuroscience 2021 (5 novembre 2021) : 1–12. http://dx.doi.org/10.1155/2021/7716214.
Texte intégralRésumé :
In recent years, due to the rise of online social platforms, social networks have more and more influence on our daily life, and social recommendation system has become one of the important research directions of recommendation system research. Because the graph structure in social networks and graph neural networks has strong representation capabilities, the application of graph neural networks in social recommendation systems has become more and more extensive, and it has also shown good results. Although graph neural networks have been successfully applied in social recommendation systems, their performance may still be limited in practical applications. The main reason is that they can only take advantage of pairs of user relations but cannot capture the higher-order relations between users. We propose a model that applies the hypergraph attention network to the social recommendation system (HASRE) to solve this problem. Specifically, we take the hypergraph’s ability to model high-order relations to capture high-order relations between users. However, because the influence of the users’ friends is different, we use the graph attention mechanism to capture the users’ attention to different friends and adaptively model selection information for the user. In order to verify the performance of the recommendation system, this paper carries out analysis experiments on three data sets related to the recommendation system. The experimental results show that HASRE outperforms the state-of-the-art method and can effectively improve the accuracy of recommendation.
43
Charbuty, Bahzad, et Abdulhakeem Othman Mohammed. « AN EMPIRICAL COMPARISON OF NEO4J AND TIGERGRAPH DATABASES FOR NETWORK CENTRALITY ». Science Journal of University of Zakho 11, no 2 (30 avril 2023) : 190–201. http://dx.doi.org/10.25271/sjuoz.2023.11.2.1068.
Texte intégralRésumé :
Graph databases have recently gained a lot of attention in areas where the relationships between data and the data itself are equally important, like the semantic web, social networks, and biological networks. A graph database is simply a database designed to store, query, and modify graphs. Recently, several graph database models have been developed. The goal of this research is to evaluate the performance of the two most popular graph databases, Neo4j and TigerGraph, for network centrality metrics including degree centrality, betweenness centrality, closeness centrality, eigenvector centrality, and PageRank. We applied those metrics to a set of real-world networks in both graph databases to see their performance. Experimental results show Neo4j outperforms TigerGraph for computing the centrality metrics used in this study, but TigerGraph performs better during the data loading phase.
44
Dhamala, Binita Kusum, Babu R. Dawadi, Pietro Manzoni et Baikuntha Kumar Acharya. « Performance Evaluation of Graph Neural Network-Based RouteNet Model with Attention Mechanism ». Future Internet 16, no 4 (29 mars 2024) : 116. http://dx.doi.org/10.3390/fi16040116.
Texte intégralRésumé :
Graph representation is recognized as an efficient method for modeling networks, precisely illustrating intricate, dynamic interactions within various entities of networks by representing entities as nodes and their relationships as edges. Leveraging the advantage of the network graph data along with deep learning technologies specialized for analyzing graph data, Graph Neural Networks (GNNs) have revolutionized the field of computer networking by effectively handling structured graph data and enabling precise predictions for various use cases such as performance modeling, routing optimization, and resource allocation. The RouteNet model, utilizing a GNN, has been effectively applied in determining Quality of Service (QoS) parameters for each source-to-destination pair in computer networks. However, a prevalent issue in the current GNN model is their struggle with generalization and capturing the complex relationships and patterns within network data. This research aims to enhance the predictive power of GNN-based models by enhancing the original RouteNet model by incorporating an attention layer into its architecture. A comparative analysis is conducted to evaluate the performance of the Modified RouteNet model against the Original RouteNet model. The effectiveness of the added attention layer has been examined to determine its impact on the overall model performance. The outcomes of this research contribute to advancing GNN-based network performance prediction, addressing the limitations of existing models, and providing reliable frameworks for predicting network delay.
45
Zhang, H., J. J. Zhou et R. Li. « Enhanced Unsupervised Graph Embedding via Hierarchical Graph Convolution Network ». Mathematical Problems in Engineering 2020 (26 juillet 2020) : 1–9. http://dx.doi.org/10.1155/2020/5702519.
Texte intégralRésumé :
Graph embedding aims to learn the low-dimensional representation of nodes in the network, which has been paid more and more attention in many graph-based tasks recently. Graph Convolution Network (GCN) is a typical deep semisupervised graph embedding model, which can acquire node representation from the complex network. However, GCN usually needs to use a lot of labeled data and additional expressive features in the graph embedding learning process, so the model cannot be effectively applied to undirected graphs with only network structure information. In this paper, we propose a novel unsupervised graph embedding method via hierarchical graph convolution network (HGCN). Firstly, HGCN builds the initial node embedding and pseudo-labels for the undirected graphs, and then further uses GCNs to learn the node embedding and update labels, finally combines HGCN output representation with the initial embedding to get the graph embedding. Furthermore, we improve the model to match the different undirected networks according to the number of network node label types. Comprehensive experiments demonstrate that our proposed HGCN and HGCN∗ can significantly enhance the performance of the node classification task.
46
Escobedo, Dr Fernando, Dr Henry Bernardo Garay Canales, Dr Eddy Miguel Aguirre Reyes, Carlos Alberto Lamadrid Vela, Oscar Napoleón Montoya Perez et Grover Enrique Caballero Jimenez. « Deep Attentional Implanted Graph Clustering Algorithm for the Visualization and Analysis of Social Networks ». Journal of Internet Services and Information Security 14, no 1 (2 mars 2024) : 153–64. http://dx.doi.org/10.58346/jisis.2024.i1.010.
Texte intégralRésumé :
As the user base expands, social network data becomes more intricate, making analyzing the interconnections between various entities challenging. Various graph visualization technologies are employed to analyze extensive and intricate network data. Network graphs inherently possess intricacy and may have overlapping elements. Graph clustering is a basic endeavor that aims to identify communities or groupings inside networks. Recent research has mostly concentrated on developing deep learning techniques to acquire a concise representation of graphs, which is then utilized with traditional clustering methods such as k-means or spectral clustering techniques. Multiplying these two-step architectures is challenging and sometimes results in unsatisfactory performance. This is mostly due to the lack of a goal-oriented graph encoding developed explicitly for the clustering job. This work introduces a novel Deep Learning (DL) method called Deep Attentional Implanted Graph Clustering (DAIGC), designed to achieve goal-oriented clustering. Our approach centers on associated graphs to thoroughly investigate both aspects of data in graphs. The proposed DAIGC technique utilizes a Graph Attention Autoencoder (GAA) to determine the significance of nearby nodes about a target node. This allows encoding a graph's topographical structure and node value into a concise representation. Based on this representation, an interior product decoder has been trained to rebuild the graph structure. The performance of the proposed approach has been evaluated on four distinct types and sizes of real-world intricate networks, varying in vertex count from 𝑁=102 𝑡𝑜 𝑁=107. The performance of the suggested methods is evaluated by comparing them with two established and commonly used graph clustering techniques. The testing findings demonstrate the effectiveness of the proposed method in terms of processing speed and visualization compared to the state-of-the-art algorithms.
47
Huang, Zongmo, Yazhou Ren, Xiaorong Pu, Shudong Huang, Zenglin Xu et Lifang He. « Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering ». Proceedings of the AAAI Conference on Artificial Intelligence 37, no 7 (26 juin 2023) : 7936–43. http://dx.doi.org/10.1609/aaai.v37i7.25960.
Texte intégralRésumé :
As one of the most important research topics in the unsupervised learning field, Multi-View Clustering (MVC) has been widely studied in the past decade and numerous MVC methods have been developed. Among these methods, the recently emerged Graph Neural Networks (GNN) shine a light on modeling both topological structure and node attributes in the form of graphs, to guide unified embedding learning and clustering. However, the effectiveness of existing GNN-based MVC methods is still limited due to the insufficient consideration in utilizing the self-supervised information and graph information, which can be reflected from the following two aspects: 1) most of these models merely use the self-supervised information to guide the feature learning and fail to realize that such information can be also applied in graph learning and sample weighting; 2) the usage of graph information is generally limited to the feature aggregation in these models, yet it also provides valuable evidence in detecting noisy samples. To this end, in this paper we propose Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering (SGDMC), which promotes the performance of GNN-based deep MVC models by making full use of the self-supervised information and graph information. Specifically, a novel attention-allocating approach that considers both the similarity of node attributes and the self-supervised information is developed to comprehensively evaluate the relevance among different nodes. Meanwhile, to alleviate the negative impact caused by noisy samples and the discrepancy of cluster structures, we further design a sample-weighting strategy based on the attention graph as well as the discrepancy between the global pseudo-labels and the local cluster assignment. Experimental results on multiple real-world datasets demonstrate the effectiveness of our method over existing approaches.
48
Zhao, Chensu, Yang Xin, Xuefeng Li, Hongliang Zhu, Yixian Yang et Yuling Chen. « An Attention-Based Graph Neural Network for Spam Bot Detection in Social Networks ». Applied Sciences 10, no 22 (18 novembre 2020) : 8160. http://dx.doi.org/10.3390/app10228160.
Texte intégralRésumé :
With the rapid development of social networks, spam bots and other anomaly accounts’ malicious behavior has become a critical information security problem threatening the social network platform. In order to reduce this threat, the existing research mainly uses feature-based detection or propagation-based detection, and it applies machine learning or graph mining algorithms to identify anomaly accounts in social networks. However, with the development of technology, spam bots are becoming more advanced, and identifying bots is still an open challenge. This paper proposes a new semi-supervised graph embedding model based on a graph attention network for spam bot detection in social networks. This approach constructs a detection model by aggregating features and neighbor relationships, and learns a complex method to integrate the different neighborhood relationships between nodes to operate the directed social graph. The new model can identify spam bots by capturing user features and two different relationships among users in social networks. We compare our method with other methods on real-world social network datasets, and the experimental results show that our proposed model achieves a significant and consistent improvement.
49
Liu, Haiqin, et Yanling Shao. « Two Kinds of Laplacian Spectra and Degree Kirchhoff Index of the Weighted Corona Networks ». Journal of Mathematics 2022 (10 février 2022) : 1–8. http://dx.doi.org/10.1155/2022/6884839.
Texte intégralRésumé :
Recently, the study related to network has aroused wide attention of the scientific community. Many problems can be usefully represented by corona graphs or networks. Meanwhile, the weight is a vital factor in characterizing some properties of real networks. In this paper, we give complete information about the signless Laplacian spectra of the weighted corona of a graph G 1 and a regular graph G 2 and the complete information about the normalized Laplacian spectra of the weighted corona of two regular graphs. The corresponding linearly independent eigenvectors of all these eigenvalues are also obtained. The spanning trees’ total number and the degree Kirchhoff index of the weighted corona graph are computed.
50
Yang, Xiaocheng, Mingyu Yan, Shirui Pan, Xiaochun Ye et Dongrui Fan. « Simple and Efficient Heterogeneous Graph Neural Network ». Proceedings of the AAAI Conference on Artificial Intelligence 37, no 9 (26 juin 2023) : 10816–24. http://dx.doi.org/10.1609/aaai.v37i9.26283.
Texte intégralRésumé :
Heterogeneous graph neural networks (HGNNs) have the powerful capability to embed rich structural and semantic information of a heterogeneous graph into node representations. Existing HGNNs inherit many mechanisms from graph neural networks (GNNs) designed for homogeneous graphs, especially the attention mechanism and the multi-layer structure. These mechanisms bring excessive complexity, but seldom work studies whether they are really effective on heterogeneous graphs. In this paper, we conduct an in-depth and detailed study of these mechanisms and propose the Simple and Efficient Heterogeneous Graph Neural Network (SeHGNN). To easily capture structural information, SeHGNN pre-computes the neighbor aggregation using a light-weight mean aggregator, which reduces complexity by removing overused neighbor attention and avoiding repeated neighbor aggregation in every training epoch. To better utilize semantic information, SeHGNN adopts the single-layer structure with long metapaths to extend the receptive field, as well as a transformer-based semantic fusion module to fuse features from different metapaths. As a result, SeHGNN exhibits the characteristics of a simple network structure, high prediction accuracy, and fast training speed. Extensive experiments on five real-world heterogeneous graphs demonstrate the superiority of SeHGNN over the state-of-the-arts on both accuracy and training speed.