Pay Attention to Multi-Channel for Improving Graph Neural Networks
Chung-Yi Lin, Shen-Lung Tung, Winston H. Hsu
International Conference on Learning (ICLR) 2023
Publication year: 2023

We propose Multi-channel Graph Attention (MGAT) to efficiently handle channel- specific representations encoded by convolutional kernels, enhancing the incorporation of attention with graph convolutional network (GCN)-based architectures. Our experiments demonstrate the effectiveness of integrating our proposed MGAT with various spatial-temporal GCN models for improving prediction performance.