Research map / Graph learning / GNN architectures
Graph Homomorphism Convolution
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 cycle patterns up to size 8 | GHC · CSL | accuracy: 10.00 ± 0.00 -> 100.0 ± 0.00 | Helped |
| use cycle patterns up to size 8 | GHC · Bipartite | accuracy: 58.03 ± 6.84 -> 100.0 ± 0.00 | Helped |
| use cycles instead of trees as homomorphism patterns (ablation) | GHC · MUTAG | accuracy: 89.28 ± 8.26 -> 87.81 ± 7.46 | Hurt |
| use cycles instead of trees as homomorphism patterns (ablation) | GHC · IMDB-BIN | accuracy: 72.10 ± 2.62 -> 70.93 ± 4.54 | Hurt |
| use cycles instead of trees as homomorphism patterns (ablation) | GHC · IMDB-MUL | accuracy: 48.60 ± 4.40 -> 47.41 ± 3.67 | Hurt |
| use homomorphism patterns up to graph index 100 | GHC · Paulus25 | accuracy: 7.14% | No clear effect |
| increase tree pattern size beyond 6 (ablation) | GHC-Tree · TU Dortmund benchmark datasets | accuracy | No clear effect |
Closest papers by meaning
- Homomorphism Expressivity of Spectral Invariant Graph Neural Networks (ICLR 2025 · similarity 0.87)
- Deep Homomorphism Networks (NeurIPS 2024 · similarity 0.86)
- Homomorphism Counts for Graph Neural Networks: All About That Basis (ICML 2024 · similarity 0.86)
- Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning (NeurIPS 2024 · similarity 0.86)
- PC-Conv: Unifying Homophily and Heterophily with Two-Fold Filtering (AAAI 2024 · similarity 0.86)
- The Generalized Skew Spectrum of Graphs (ICML 2025 · similarity 0.85)
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.