Research map / Graph learning / GNN architectures
Autobahn: Automorphism-based Graph Neural Nets
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 |
|---|---|---|---|
| add cycle-based convolutions (ablation) | Autobahn · Zinc (subset) | validation loss: 0.175 ± 0.004 -> 0.124 ± 0.001 | Helped |
| add paths shorter than the maximum length considered (ablation) | Autobahn · Zinc (subset) | validation loss: 0.167 ± 0.001 -> 0.124 ± 0.001 | Helped |
| increase maximum path length from 4 to 7 (ablation) | Autobahn · Zinc (subset) | validation loss: 0.140 ± 0.000 -> 0.121 ± 0.001 | Helped |
| increase maximum path length from 4 to 7 (ablation) | Autobahn · Zinc (subset) | training time: 3 hour 15 minute -> 9 hour 30 minute | Hurt |
Closest papers by meaning
- Schur Nets: exploiting local structure for equivariance in higher order graph neural networks (NeurIPS 2024 · similarity 0.89)
- AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks (AAAI 2025 · similarity 0.89)
- Deep Homomorphism Networks (NeurIPS 2024 · similarity 0.88)
- The quest for the GRAph Level autoEncoder (GRALE) (NeurIPS 2025 · similarity 0.87)
- Equivalence is All: A Unified View for Self-supervised Graph Learning (ICML 2025 · similarity 0.87)
- Homomorphism Counts for Graph Neural Networks: All About That Basis (ICML 2024 · similarity 0.87)
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.