[2402.14730] Clifford-Steerable Convolutional Neural Networks
Abstract:We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces $\mathbb{R}^{p,q}$. They cover, for instance, $\mathrm{E}(3)$-equivariance on $\mathbb{R}^3$ and Poincaré-equivariance on Minkowski spacetime $\mathbb{R}^{1,3}$. Our approach is based on an implicit parametrization of $\mathrm{O}(p,q)$-steerable kernels via Clifford group equivariant neural networks. We significantly and consistently outperform baseline methods on fluid dynamics as well as relativistic electrodynamics forecasting tasks.
View PDF HTML (experimental) Abstract:We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces $\mathbb{R}^{p,q}$. They cover, for instance, $\mathrm{E}(3)$-equivariance on $\mathbb{R}^3$ and Poincaré-equivariance on Minkowski spacetime $\mathbb{R}^{1,3}$. Our approach is based on an implicit parametrization of $\mathrm{O}(p,q)$-steerable kernels via Clifford group equivariant neural networks. We significantly and consistently outperform baseline methods on fluid…
saved by
related reading
- [2212.02493] Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fieldsarxiv.org
- 1802.08219arxiv.org
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugesarxiv.org
- [2404.19756] KAN: Kolmogorov-Arnold Networksarxiv.org
- Naturally Occurring Equivariance in Neural Networksdistill.pub
- [2205.09653] Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networksarxiv.org
- Structured State Spaces: Combining Continuous-Time, Recurrent, and Convolutional Models · Hazy Researchhazyresearch.stanford.edu
- Scale-invariant-CNNs/docs/Report/Implementation.md at master · ruoqizzz/Scale-invariant-CNNsgithub.com
- Neural Manifold Ordinary Differential Equationsarxiv.org
- Understanding Convolutions on Graphsdistill.pub
- [2111.00396] Efficiently Modeling Long Sequences with Structured State Spacesarxiv.org
- Statistical Mechanics of Deep Learningganguli-gang.stanford.edu