Research map / Architectures and efficiency / CNN design
A General Framework for Equivariant Neural Networks on Reductive Lie Groups
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 the proposed PointMACE architecture with O(3) symmetry instead of PointNet++ | 3D point-cloud shape recognition · ModelNet10 | accuracy: 95.0 -> 96.1 | Helped |
| Use the proposed LorentzMACE architecture instead of LorentzNet | Lorentz-equivariant jet tagging · Top-Tagging | Rej30%: 2195 ± 173 -> 1935 ± 85 | Hurt |
| Use the proposed LorentzMACE architecture instead of PELICAN | Lorentz-equivariant jet tagging · Top-Tagging | accuracy: 0.942 -> 0.942 | No clear effect |
Closest papers by meaning
- Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups (ICLR 2025 · similarity 0.91)
- Lie Group Decompositions for Equivariant Neural Networks (ICLR 2024 · similarity 0.91)
- Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras (ICML 2024 · similarity 0.89)
- Compact Matrix Quantum Group Equivariant Neural Networks (ICML 2025 · similarity 0.87)
- Explicit Discovery of Nonlinear Symmetries from Dynamic Data (ICML 2025 · similarity 0.86)
- GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras (ICML 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.