Graph Adaptive Attention Network with Cross-Entropy

• Published in: Entropy (Basel, Switzerland) Vol. 26; no. 7; p. 576
• Main Author: Chen, Zhao
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.07.2024
• Subjects: adaptive attention mechanism; Artificial neural networks; Back propagation; Classification; cross-entropy; Deep learning; Efficiency; Entropy; Fourier transforms; GCN; Graphs; Methods; multi-head graph convolution; Neural networks; Nodes; non-Euclidean; Optimization techniques; Recommender systems; Signal processing; Social networks; Wavelet transforms; non-Euclidean; adaptive attention mechanism; GCN; cross-entropy; multi-head graph convolution

Non-Euclidean data, such as social networks and citation relationships between documents, have node and structural information. The Graph Convolutional Network (GCN) can automatically learn node features and association information between nodes. The core ideology of the Graph Convolutional Network...