MC-GAT: Multi-channel Graph Attention Networks for capturing diverse information in complex graph

Abstract Much attention has been paid to Graph Attention Networks (GAT), which excel at various analytical tasks involving graph and network data. However, complex real-world networks have both edge topology and node features. GAT only relies on the topology of edges to extract network information, and the association between node features is underutilized, which may seriously hinder GAT's expressive ability on some tasks. In addition, the attention mechanism can automatically assign different weights to different pieces of information, making it easier to express information with multiple aspects. Therefore, we propose semi-supervised multi-channel attention networks (MC-GAT), which simultaneously extract node futures, topological structures, and their combinations. To create node embeddings containing various informational aspects, we then use the attention mechanism to assign weights to each of them. Extensive testing on benchmark datasets has shown us to be at our best. The performance of the proposed model is demonstrated by the fact that MC-GAT achieves relative maximum improvements of 4.22% for accuracy (ACC) on BlogCatalog and 5.23% for macro F1-score (F1) on UAI2010. The proposed model is available at https://github.com/123123-2/LZY/tree/main/AM-GCN-master.