Research map / Graph learning / GNN architectures
Universal Invariant and Equivariant Graph Neural 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 |
|---|---|---|---|
| Increase tensorization order from 1 to 2 or 3 (ablation) | One-layer invariant and equivariant GNNs · Synthetic graphs with 5 and 10 nodes; geodesic diameter and per-node longest shortest-path tasks | testing MSE | Helped |
| Increase width S (ablation) | One-layer invariant and equivariant GNNs · Synthetic graphs with 5 and 10 nodes; geodesic diameter and per-node longest shortest-path tasks | testing MSE | Mixed |
Closest papers by meaning
- Universally Invariant Learning in Equivariant GNNs (NeurIPS 2025 · similarity 0.92)
- On Universality Classes of Equivariant Networks (NeurIPS 2025 · similarity 0.91)
- A Characterization Theorem for Equivariant Networks with Point-wise Activations (ICLR 2024 · similarity 0.91)
- Graph Automorphism Group Equivariant Neural Networks (ICML 2024 · similarity 0.91)
- Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks? (NeurIPS 2024 · similarity 0.90)
- Schur Nets: exploiting local structure for equivariance in higher order graph neural networks (NeurIPS 2024 · similarity 0.89)
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.