Platonic Transformers: A Solid Choice For Equivariance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Islam, Mohammad Mohaiminul, Anand, Rishabh, Wessels, David R., de Kruiff, Friso, Kuipers, Thijs P., Ying, Rex, Sánchez, Clara I., Vadgama, Sharvaree, Bökman, Georg, Bekkers, Erik J.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916995831693312
author Islam, Mohammad Mohaiminul
Anand, Rishabh
Wessels, David R.
de Kruiff, Friso
Kuipers, Thijs P.
Ying, Rex
Sánchez, Clara I.
Vadgama, Sharvaree
Bökman, Georg
Bekkers, Erik J.
author_facet Islam, Mohammad Mohaiminul
Anand, Rishabh
Wessels, David R.
de Kruiff, Friso
Kuipers, Thijs P.
Ying, Rex
Sánchez, Clara I.
Vadgama, Sharvaree
Bökman, Georg
Bekkers, Erik J.
contents While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision. Existing equivariant methods often sacrifice the efficiency and flexibility that make Transformers so effective through complex, computationally intensive designs. We introduce the Platonic Transformer to resolve this trade-off. By defining attention relative to reference frames from the Platonic solid symmetry groups, our method induces a principled weight-sharing scheme. This enables combined equivariance to continuous translations and Platonic symmetries, while preserving the exact architecture and computational cost of a standard Transformer. Furthermore, we show that this attention is formally equivalent to a dynamic group convolution, which reveals that the model learns adaptive geometric filters and enables a highly scalable, linear-time convolutional variant. Across diverse benchmarks in computer vision (CIFAR-10), 3D point clouds (ScanObjectNN), and molecular property prediction (QM9, OMol25), the Platonic Transformer achieves competitive performance by leveraging these geometric constraints at no additional cost.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03511
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Platonic Transformers: A Solid Choice For Equivariance
Islam, Mohammad Mohaiminul
Anand, Rishabh
Wessels, David R.
de Kruiff, Friso
Kuipers, Thijs P.
Ying, Rex
Sánchez, Clara I.
Vadgama, Sharvaree
Bökman, Georg
Bekkers, Erik J.
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Image and Video Processing
While widespread, Transformers lack inductive biases for geometric symmetries common in science and computer vision. Existing equivariant methods often sacrifice the efficiency and flexibility that make Transformers so effective through complex, computationally intensive designs. We introduce the Platonic Transformer to resolve this trade-off. By defining attention relative to reference frames from the Platonic solid symmetry groups, our method induces a principled weight-sharing scheme. This enables combined equivariance to continuous translations and Platonic symmetries, while preserving the exact architecture and computational cost of a standard Transformer. Furthermore, we show that this attention is formally equivalent to a dynamic group convolution, which reveals that the model learns adaptive geometric filters and enables a highly scalable, linear-time convolutional variant. Across diverse benchmarks in computer vision (CIFAR-10), 3D point clouds (ScanObjectNN), and molecular property prediction (QM9, OMol25), the Platonic Transformer achieves competitive performance by leveraging these geometric constraints at no additional cost.
title Platonic Transformers: A Solid Choice For Equivariance
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2510.03511