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
• DOI: 10.3390/e26070576
• ISSN: 1099-4300

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 is to aggregate node information by using edge information, thereby generating a new node feature. In updating node features, there are two core influencing factors. One is the number of neighboring nodes of the central node; the other is the contribution of the neighboring nodes to the central node. Due to the previous GCN methods not simultaneously considering the numbers and different contributions of neighboring nodes to the central node, we design the adaptive attention mechanism (AAM). To further enhance the representational capability of the model, we utilize Multi-Head Graph Convolution (MHGC). Finally, we adopt the cross-entropy (CE) loss function to describe the difference between the predicted results of node categories and the ground truth (GT). Combined with backpropagation, this ultimately achieves accurate node classification. Based on the AAM, MHGC, and CE, we contrive the novel Graph Adaptive Attention Network (GAAN). The experiments show that classification accuracy achieves outstanding performances on Cora, Citeseer, and Pubmed datasets.