paper-with-me

홈 › Papers

Equivariant and Steerable Neural Networks: A review with special emphasis on the symmetric group

2023-01-08 · Patrick Krüger, Hanno Gottschalk

Convolutional neural networks revolutionized computer vision and natrual language processing. Their efficiency, as compared to fully connected neural networks, has its origin in the architecture, where convolutions reflect the translation invariance in space and time in pattern or speech recognition tasks. Recently, Cohen and Welling have put this in the broader perspective of invariance under symmetry groups, which leads to the concept of group equivaiant neural networks and more generally steerable neural networks. In this article, we review the architecture of such networks including equivariant layers and filter banks, activation with capsules and group pooling. We apply this formalism to the symmetric group, for which we work out a number of details on representations and capsules that are not found in the literature.

📄 PDF Abstract BibTeX arXiv:2301.03019

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech RecognitionTranslation

Similar Papers 제목 키워드 기반

Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?

2024-10-15 · Jiacheng Cen, Anyi Li, Ning Lin, Yuxiang Ren 외

Equivariant Graph Neural Networks (GNNs) that incorporate E(3) symmetry have achieved significant success in various scientific applications. As one of the most successful models, EGNN leverages a simple scalarization te…

Integrating Symmetry into Differentiable Planning with Steerable Convolutions

2022-06-08 · Linfeng Zhao, Xupeng Zhu, Lingzhi Kong, Robin Walters 외

We study how group symmetry helps improve data efficiency and generalization for end-to-end differentiable planning algorithms when symmetry appears in decision-making tasks. Motivated by equivariant convolution networks…

Decision MakingVisual Navigation

Steerable Transformers

2024-05-24 · Soumyabrata Kundu, Risi Kondor

In this work we introduce Steerable Transformers, an extension of the Vision Transformer mechanism that maintains equivariance to the special Euclidean group $\mathrm{SE}(d)$. We propose an equivariant attention mechanis…

Learning Symmetric Representations for Equivariant World Models

2021-09-29 · Jung Yeon Park, Ondrej Biza, Linfeng Zhao, Jan-Willem van de Meent 외

Encoding known symmetries into world models can improve generalization. However, identifying how latent symmetries manifest in the input space can be difficult. As an example, rotations of objects are equivariant with re…

Inductive Bias

Geometric and Physical Quantities Improve E(3) Equivariant Message Passing

2021-10-06 · ICLR 2022 4 · Johannes Brandstetter, Rob Hesselink, Elise van der Pol, Erik J Bekkers 외

Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that ge…

Graph Property Prediction