SL(n) Representation Learning: An Intrinsic Mixed-Curvature Space with Higher Curvature Capacities and Deeper Order-Aware Composition
cs.LG
Submitted: 2026-09-14
Updated: 2026-09-19
Comments: 35 pages, 8 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Testing the Manifold Hypothesis
- Building Deep Networks on Grassmann Manifolds
- Chern connection of a pseudo-Finsler metric as a family of affine connections
- Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie Algebras
- Product Manifold Representations for Learning on Biological Pathways
- Lie Group Decompositions for Equivariant Neural Networks
- Improving Heterogeneous Graph Learning with Weighted Mixed-Curvature Product Manifold
- A Self-supervised Mixed-curvature Graph Neural Network
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks