Research map / Graph learning / GNN architectures
Simplified Graph Convolution with Heterophily
Sudhanshu Chanpuriya, Cameron N Musco
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 ASGC (adaptive Krylov filter) instead of SGC | SGC · Chameleon | accuracy: 57.70 -> 72.28 | Improved |
| use ASGC instead of SGC | SGC · Squirrel | accuracy: 44.98 -> 58.98 | Improved |
| use ASGC instead of SGC | SGC · Texas | accuracy: 55.68 -> 86.76 | Improved |
| use ASGC instead of SGC | SGC · Cornell | accuracy: 54.32 -> 86.22 | Improved |
| use ASGC instead of SGC | SGC · Actor | accuracy: 30.07 -> 36.45 | Improved |
| use ASGC instead of SGC | SGC · PubMed | accuracy: 73.90 -> 79.05 | Improved |
| use ASGC instead of SGC on homophilous Cora | SGC · Cora | accuracy: 78.16 -> 73.93 | Hurt |
| use ASGC instead of SGC on homophilous Citeseer | SGC · Citeseer | accuracy: 70.18 -> 67.73 | Hurt |
| use ASGC instead of SGC on Computers and Photo | SGC · Computers | accuracy: 87.14 -> 86.72 | No clear effect |
| use ASGC instead of GPRGNN on Texas | GPRGNN · Texas | accuracy: 92.92 -> 86.76 | Hurt |
| use ASGC instead of GPRGNN on Chameleon | GPRGNN · Chameleon | accuracy: 67.48 -> 72.28 | Improved |
| use ASGC instead of GCN on Chameleon | GCN · Chameleon | accuracy: 60.96 -> 72.28 | Improved |
Closest papers by meaning
- Powerful Graph Convolutional Networks with Adaptive Propagation Mechanism for Homophily and Heterophily (AAAI 2022 · similarity 0.91)
- Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks (AAAI 2024 · similarity 0.89)
- PC-Conv: Unifying Homophily and Heterophily with Two-Fold Filtering (AAAI 2024 · similarity 0.88)
- Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective (NeurIPS 2025 · similarity 0.88)
- Understanding Heterophily for Graph Neural Networks (ICML 2024 · similarity 0.88)
- Generalizing CNNs to graphs with learnable neighborhood quantization (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.
