Results 1 to 10 of about 106,924 (261)
High-order graph attention network [PDF]
Information Sciences, 2023 GCN is a widely-used representation learning method for capturing hidden features in graph data. However, traditional GCNs suffer from the oversmoothing problem, hindering their ability to extract high-order information and obtain robust data representation.
Liang Bai, Xian Yang, Hangyuan Du
exaly +3 more sources
Directional Graph Attention Networks
, 2023 In recent years, graph neural networks (GNNs) have become a promising method for analyzing data structured in graph format. By considering connections between entities in a graph, GNNs are able to extract valuable insights. One notable variation of GNN is the graph attention network (GAT), which employs the attention mechanism and has demonstrated ...
Sitao Luan, Jiaqi Zhu
openaire +2 more sources
Heterophily-aware graph attention network
Pattern Recognition, 2023 Graph Neural Networks (GNNs) have shown remarkable success in graph representation learning. Unfortunately, current weight assignment schemes in standard GNNs, such as the calculation based on node degrees or pair-wise representations, can hardly be effective in processing the networks with heterophily, in which the connected nodes usually possess ...
Junfu Wang +3 more
openaire +3 more sources
SGAT: Simplicial Graph Attention Network
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022 Heterogeneous graphs have multiple node and edge types and are semantically richer than homogeneous graphs. To learn such complex semantics, many graph neural network approaches for heterogeneous graphs use metapaths to capture multi-hop interactions between nodes.
See Hian Lee, Feng Ji, Wee Peng Tay
openaire +4 more sources
Hyperbolic Graph Attention Network [PDF]
IEEE Transactions on Big Data, 2021 Graph neural network (GNN) has shown superior performance in dealing with graphs, which has attracted considerable research attention recently. However, most of the existing GNN models are primarily designed for graphs in Euclidean spaces. Recent research has proven that the graph data exhibits non-Euclidean latent anatomy.
Yiding Zhang +4 more
openaire +2 more sources
Sparse Graph Attention Networks [PDF]
IEEE Transactions on Knowledge and Data Engineering, 2023 Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node classification, link prediction and graph classification.
Yang Ye, Shihao Ji 0001
openaire +2 more sources
Graph Ordering Attention Networks
Proceedings of the AAAI Conference on Artificial Intelligence, 2023 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.
Michail Chatzianastasis +3 more
openaire +2 more sources
Heterogeneous Graph Attention Network [PDF]
The World Wide Web Conference, 2019 10 ...
Xiao Wang 0017 +6 more
openaire +2 more sources
A Regularized Attention Mechanism for Graph Attention Networks [PDF]
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020 Machine learning models that can exploit the inherent structure in data have gained prominence. In particular, there is a surge in deep learning solutions for graph-structured data, due to its wide-spread applicability in several fields. Graph attention networks (GAT), a recent addition to the broad class of feature learning models in graphs, utilizes ...
Uday Shankar Shanthamallu +2 more
openaire +2 more sources
GAEN: Graph Attention Evolving Networks [PDF]
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021 Real-world networked systems often show dynamic properties with continuously evolving network nodes and topology over time. When learning from dynamic networks, it is beneficial to correlate all temporal networks to fully capture the similarity/relevance between nodes. Recent work for dynamic network representation learning typically trains each single
Min Shi 0001 +5 more
openaire +1 more source