The reviewed record of science sign in
Pith

arxiv: 2407.01049 · v2 · pith:K5KWZKZX · submitted 2024-07-01 · cs.LG

SE(3)-Hyena Operator for Scalable Equivariant Learning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:K5KWZKZXrecord.jsonopen to challenge →

classification cs.LG
keywords equivarianthyenacontextwhilegeometricglobaloperatorcomplexity
0
0 comments X
read the original abstract

Modeling global geometric context while maintaining equivariance is crucial for accurate predictions in many fields such as biology, chemistry, or vision. Yet, this is challenging due to the computational demands of processing high-dimensional data at scale. Existing approaches such as equivariant self-attention or distance-based message passing, suffer from quadratic complexity with respect to sequence length, while localized methods sacrifice global information. Inspired by the recent success of state-space and long-convolutional models, in this work, we introduce SE(3)-Hyena operator, an equivariant long-convolutional model based on the Hyena operator. The SE(3)-Hyena captures global geometric context at sub-quadratic complexity while maintaining equivariance to rotations and translations. Evaluated on equivariant associative recall and n-body modeling, SE(3)-Hyena matches or outperforms equivariant self-attention while requiring significantly less memory and computational resources for long sequences. Our model processes the geometric context of 20k tokens x3.5 times faster than the equivariant transformer and allows x175 longer a context within the same memory budget.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Fast contracted Clebsch--Gordan tensor products for equivariant graph neural networks

    physics.comp-ph 2026-05 unverdicted novelty 7.0

    An O(L^3) algorithm computes contracted Clebsch-Gordan tensor products for equivariant ML potentials using a structured angular grid and spherical Poisson bracket to handle parity-odd terms at fixed CP rank.