Research map / Graph learning / GNN architectures
Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
Yimeng Min, Frederik Wenkel, Guy Wolf
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use Scattering GCN instead of GAT | Scattering GCN · DBLP | accuracy: 66.1 -> 81.5 | Improved |
| use Scattering GCN instead of GCN | Scattering GCN · Cora | accuracy: 81.5 -> 84.2 | Improved |
| use Scattering GCN instead of GCN | Scattering GCN · Pubmed | accuracy: 79.0 -> 79.4 | Improved |
| use Scattering GCN instead of GAT | Scattering GCN · Citeseer | accuracy: 72.5 -> 71.7 | Hurt |
| add band-pass scattering channels and residual convolution to GCN | GCN · DBLP | accuracy: 59.3 -> 81.5 | Improved |
| add GCN channels to pure graph scattering | Graph scattering baseline · Pubmed | accuracy: 69.8 -> 79.4 | Improved |
| add GCN channels to pure graph scattering | Graph scattering baseline · Cora | accuracy: 81.9 -> 84.2 | Improved |
Closest papers by meaning
- Pruned Graph Scattering Transforms (ICLR 2020 · similarity 0.92)
- Efficient and Stable Graph Scattering Transforms via Pruning (TPAMI 2020 · similarity 0.91)
- Graph Neural Networks Do Not Always Oversmooth (NeurIPS 2024 · similarity 0.90)
- Dissecting the Diffusion Process in Linear Graph Convolutional Networks (NeurIPS 2021 · similarity 0.90)
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning (ICLR 2025 · similarity 0.88)
- Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
