Spacetime $E(n)$-Transformer: Equivariant Attention for Spatio-temporal Graphs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Charles, Sergio G.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911984004366336
author Charles, Sergio G.
author_facet Charles, Sergio G.
contents We introduce an $E(n)$-equivariant Transformer architecture for spatio-temporal graph data. By imposing rotation, translation, and permutation equivariance inductive biases in both space and time, we show that the Spacetime $E(n)$-Transformer (SET) outperforms purely spatial and temporal models without symmetry-preserving properties. We benchmark SET against said models on the charged $N$-body problem, a simple physical system with complex dynamics. While existing spatio-temporal graph neural networks focus on sequential modeling, we empirically demonstrate that leveraging underlying domain symmetries yields considerable improvements for modeling dynamical systems on graphs.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06039
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spacetime $E(n)$-Transformer: Equivariant Attention for Spatio-temporal Graphs
Charles, Sergio G.
Machine Learning
Artificial Intelligence
We introduce an $E(n)$-equivariant Transformer architecture for spatio-temporal graph data. By imposing rotation, translation, and permutation equivariance inductive biases in both space and time, we show that the Spacetime $E(n)$-Transformer (SET) outperforms purely spatial and temporal models without symmetry-preserving properties. We benchmark SET against said models on the charged $N$-body problem, a simple physical system with complex dynamics. While existing spatio-temporal graph neural networks focus on sequential modeling, we empirically demonstrate that leveraging underlying domain symmetries yields considerable improvements for modeling dynamical systems on graphs.
title Spacetime $E(n)$-Transformer: Equivariant Attention for Spatio-temporal Graphs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.06039