Research map / Graph learning / GNN architectures
Beyond Low-frequency Information in Graph Convolutional Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 FAGCN instead of GraphHeat | Node classification · Cora | accuracy: 83.7\% -> 84.1$\pm$0.5\% | Helped |
| Use FAGCN instead of GraphHeat | Node classification · Citeseer | accuracy: 72.5\% -> 72.7$\pm$0.8\% | Helped |
| Use FAGCN instead of GraphHeat | Node classification · Pubmed | accuracy: 80.5\% -> 79.4$\pm$0.3\% | Hurt |
| Use FAGCN instead of MLP | Node classification · Cham-3 | accuracy: 74.3\% -> 76.1\% | Helped |
| Use FAGCN instead of Geom-GCN | Node classification · Squi-3 | accuracy: 63.3\% -> 66.7\% | Helped |
| Use FAGCN instead of GCN | Node classification · Cham-5 | accuracy: 59.8\% -> 61.7\% | Helped |
| Use FAGCN instead of Geom-GCN | Node classification · Squi-5 | accuracy: 38.1\% -> 39.7\% | Helped |
| Combine low- and high-frequency signals adaptively rather than using low-frequency signals alone | Synthetic node classification networks · Networks with increasing inter-class connection probability | accuracy | Mixed |
| Increase model depth | GCN · Networks of different assortativity | accuracy | Hurt |
| Increase model depth | FAGCN · Networks of different assortativity | accuracy | No clear effect |
| Use high-frequency rather than low-frequency signals as inter-class connection probability increases | Synthetic node classification · Synthetic networks | accuracy | Mixed |
Closest papers by meaning
- EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs (AAAI 2020 · similarity 0.88)
- Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective (ICLR 2025 · similarity 0.88)
- Generalizing CNNs to graphs with learnable neighborhood quantization (NeurIPS 2024 · similarity 0.87)
- How Graph Neural Networks Learn: Lessons from Training Dynamics (ICML 2024 · similarity 0.86)
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective (NeurIPS 2025 · similarity 0.86)
- Edge Prompt Tuning for Graph Neural Networks (ICLR 2025 · similarity 0.86)
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.