Skip to yearly menu bar Skip to main content

Virtual oral
Affinity Workshop: Tiny Papers Showcase Day (a DEI initiative)

Pay Attention to Multi-Channel for Improving Graph Neural Networks

Chung-Yi Lin


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.

Chat is not available.