| Paper ID | SS-16.3 |
| Paper Title |
GEOMETRIC SCATTERING ATTENTION NETWORKS |
| Authors |
Yimeng Min, Frederik Wenkel, Guy Wolf, Université de Montréal; Mila - Quebec AI Institute, Canada |
| Session | SS-16: Theoretical Foundations of Graph Neural Networks |
| Location | Gather.Town |
| Session Time: | Friday, 11 June, 14:00 - 14:45 |
| Presentation Time: | Friday, 11 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Special Sessions: Theoretical Foundations of Graph Neural Networks |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Geometric scattering has recently gained recognition in graph representation learning, and recent work has shown that integrating scattering features in graph convolution networks (GCNs) can alleviate the typical oversmoothing of features in node representation learning. However, scattering often relies on handcrafted design, requiring careful selection of frequency bands via a cascade of wavelet transforms, as well as an effective weight sharing scheme to combine low- and band-pass information. Here, we introduce a new attention-based architecture to produce adaptive task-driven node representations by implicitly learning node-wise weights for combining multiple scattering and GCN channels in the network. We show the resulting geometric scattering attention network (GSAN) outperforms previous networks in semi-supervised node classification, while also enabling a spectral study of extracted information by examining node-wise attention weights. |
