PAY ATTENTION TO MULTI-CHANNEL FOR IMPROVING GRAPH NEURAL NETWORKS
Journal
1st Tiny Papers Track at ICLR 2023 - Tiny Papers @ ICLR 2023
Date Issued
2023-05
Author(s)
Abstract
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.
Event(s)
1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023
Publisher
International Conference on Learning Representations, ICLR
Type
conference paper