SO(3)-Equivariant Neural Networks for Learning from Scalar and Vector Fields on Spheres
cs.LG
Submitted: 2025-03-12
Updated: 2026-03-31
DOI: 10.5617/nmi.13275
Code: https://github.com/ballerin/GsCNNs
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Adam: A Method for Stochastic Optimization
- PEAR: Equal Area Weather Forecasting on the Sphere
- GenCast: Diffusion-based ensemble forecasting for medium-range weather
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis