IEEE

Enhancing Graph Structure Learning via Motif-Driven Hypergraph Construction

Abstract: Graph neural networks (GNNs), as a cutting-edge technology in deep learning, perform particularly well in various tasks that process graph structure data. However, their foundation on ...
IEEE

Semi-Supervised Graph Structure Learning via Dual Reinforcement of Label and Prior Structure

Abstract: Graph neural networks (GNNs) have achieved considerable success in dealing with graph-structured data by the message-passing mechanism. Actually, this mechanism relies on a fundamental ...