Research map / Learning theory and algorithms / Matrix and tensor methods
Clifford Group Equivariant 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 |
|---|---|---|---|
| use Clifford group equivariant layers instead of EGNN scalarization | n-body GNN · n-body system | MSE: 0.0070 -> 0.0039 | Helped |
| use CGENN instead of SEGNN | n-body GNN · n-body system | MSE: 0.0043 -> 0.0039 | Helped |
| use CGENN instead of LorentzNet | top tagging GNN · Top tagging | 1/eps_B at eps_S=0.5: 498 -> 500 | No clear effect |
| use CGENN instead of LorentzNet | top tagging GNN · Top tagging | 1/eps_B at eps_S=0.3: 2195 -> 2172 | No clear effect |
| use CGENN instead of LorentzNet | top tagging GNN · Top tagging | AUC: 0.9868 -> 0.9869 | No clear effect |
| use CGENN instead of LGN (steerable) | top tagging GNN · Top tagging | accuracy: 0.929 -> 0.942 | Helped |
| use CGENN instead of EGNN (scalarization) | top tagging GNN · Top tagging | accuracy: 0.922 -> 0.942 | Helped |
| use CGENN instead of scalarization baselines (VN, GVP, EGNN-MLP) on signed volume | CGENN · O(3) signed volume | MSE | Helped |
| use CGENN instead of MLP on signed volume | CGENN · O(3) signed volume | MSE | Helped |
| use CGENN at 256 training points | CGENN · O(5) convex hull | MSE | Hurt |
| use CGENN with 30 and 100 training samples | CGENN · O(5) regression | MSE | Hurt |
| use CGENN with 300 or more training samples | CGENN · O(5) regression | MSE | Helped |
Closest papers by meaning
- GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras (ICML 2025 · similarity 0.91)
- Clifford Group Equivariant Simplicial Message Passing Networks (ICLR 2024 · similarity 0.88)
- Lie Group Decompositions for Equivariant Neural Networks (ICLR 2024 · similarity 0.88)
- Clifford-Steerable Convolutional Neural Networks (ICML 2024 · similarity 0.88)
- Compact Matrix Quantum Group Equivariant Neural Networks (ICML 2025 · similarity 0.88)
- Graph Automorphism Group Equivariant Neural Networks (ICML 2024 · 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.