Pay Attention to Multi-Channel for Improving Graph Neural Networks
Chung-Yi Lin
2023 Virtual oral
in
Affinity Event: Tiny Papers Showcase Day (a DEI initiative)
in
Affinity Event: Tiny Papers Showcase Day (a DEI initiative)
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.
Video
Chat is not available.
Successful Page Load