@inproceedings{zhdanov2024clifford-steerable,
author = {Zhdanov, Maksim and Ruhe, David and Weiler, Maurice and Lucic, Ana and Brandstetter, Johannes and Forr'e, Patrick},
title = {Clifford-Steerable Convolutional Neural Networks},
booktitle = {ICML 2024},
year = {2024},
month = {February},
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 Poincar\'e-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.},
url = {http://approjects.co.za/?big=en-us/research/publication/clifford-steerable-convolutional-neural-networks/},
}