Self-Attention Empowered Graph Convolutional Network for Structure Learning and Node Embedding

arXiv:2403.03465v1 Announce Type: new
Abstract: In representation learning on graph-structured data, many popular graph neural networks (GNNs) fail to capture long-range dependencies, leading to performance degradation. Furthermore, this weakness is magnified when the concerned graph is characterized by heterophily (low homophily). To solve this issue, this paper proposes a novel graph learning framework called the graph convolutional network with self-attention (GCN-SA). The proposed scheme exhibits an exceptional generalization capability in node-level representation learning. The proposed GCN-SA contains two enhancements corresponding …

abstract arxiv attention cs.lg cs.si data dependencies embedding gnns graph graph neural networks issue low network networks neural networks node paper performance popular representation representation learning self-attention solve structured data type