Equivariant neural networks (ENNs) have been shown to be extremely effective in applications involving underlying symmetries. By construction ENNs cannot produce lower symmetry outputs given a higher symmetry input. However, symmetry breaking occurs in many physical systems and we may obtain a less symmetric stable state from an initial highly symmetric one. Hence, it is imperative that we understand how to systematically break symmetry in ENNs. In this work, we propose a novel symmetry breaking framework that is fully equivariant and is the first which fully addresses spontaneous symmetry breaking. We emphasize that our approach is general and applicable to equivariance under any group. To achieve this, we introduce the idea of symmetry breaking sets (SBS). Rather than redesign existing networks, we design sets of symmetry breaking objects which we feed into our network based on the symmetry of our inputs and outputs. We show there is a natural way to define equivariance on these sets, which gives an additional constraint. Minimizing the size of these sets equates to data efficiency. We prove that minimizing these sets translates to a well studied group theory problem, and tabulate solutions to this problem for the point groups. Finally, we provide some examples of symmetry breaking to demonstrate how our approach works in practice. The code for these examples is available at \url{https://github.com/atomicarchitects/equivariant-SBS}.
Equivariant Flow Matching for Symmetry-Breaking Bifurcation Problems
Department of Mechanical Engineering, Eindhoven University of Technology(埃因霍温理工大学机械工程系);DIFFER – Dutch Institute for Fundamental Energy Research(荷兰基础能源研究所);Faculty of Civil Engineering, Department of Mechanics, Czech Technical University in Prague(布拉格捷克技术大学土木工程学院力学系);Department of Mathematics and Computer Science, Eindhoven University of Technology(埃因霍温理工大学数学与计算机科学系)
Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments
School of Mechanical Engineering, Yonsei University, Seoul, South Korea(延世大学机械工程学院,首尔,韩国);Department of Artificial Intelligence, Yonsei University, Seoul, South Korea(延世大学人工智能系,首尔,韩国);Department of Mechanical Engineering, University of California, Berkeley, United States(加州大学伯克利分校机械工程系,美国)
Learning (Approximately) Equivariant Networks via Constrained Optimization
Computer Science Department, University of Stuttgart(斯图加特大学计算机科学系);International Max Planck Research School for Intelligent Systems(国际马克斯·普朗克智能系统研究学校);Department of Applied Mathematics, École Polytechnique de Paris(巴黎高等理工学院应用数学系)
Weizmann Institute of Science(魏茨曼科学研究所);Department of Computer Science and Applied Mathematics(计算机科学与应用数学系)
使用对排列不变或等变的深度神经网络来学习无序集合上的函数已经变得普遍。最流行的基本模型是DeepSets [Zaheer et al. 2017]和PointNet [Qi et al. 2017]。虽然已知DeepSets和PointNet对于近似不变函数是通用的,但在近似\emph{equivariant}集合函数时并不通用。另一方面,最近的几个等变集架构已被证明是等变泛的[Sannai et al. 2019],[Keriven et al. 2019],然而这些模型要么使用不是置换等变的层(在标准意义上)和/或使用较不实用的高阶张量变量。因此,在理解流行的同变集模型与理论模型的普遍性方面存在差距。在本文中,我们通过证明:(i)PointNet不是等变通用的;(ii)添加单个线性传输层使PointNet通用。我们称这种架构PointNetST,并认为它是迄今为止已知的最简单的置换等变通用模型。另一个结果是DeepSets是通用的,PointNetSeg,一种流行的点云分割网络(例如,在[Qi et al. 2017]中使用)也是通用的。用于证明上述结果的关键理论工具是所有置换等变多项式层的显式表征。最后,我们提供了数值实验验证理论结果和比较不同的置换等变模型。
NVIDIA Research(英伟达研究院);Stanford University(斯坦福大学);Bar Ilan University(巴伊兰大学)
从无序集合中学习是一种基本的学习方法,近年来受到越来越多的关注。这方面的研究集中在集合的元素由特征向量表示的情况下,而很少强调集合元素本身坚持自己的对称性的常见情况。这种情况与许多应用相关,从去模糊图像突发到多视图3D形状识别和重建。在本文中,我们提出了一个原则性的方法来学习一般对称元素的集合。我们首先描述的线性层的空间是等变的元素重新排序和元素的固有对称性,如在图像的情况下的翻译。我们进一步表明,由这些层组成的网络,称为Deep Sets for Symmetric Elements(DSS)层,是不变函数和等变函数的通用逼近器,并且这些网络比暹罗网络更有表现力。DSS层也很容易实现。最后,我们证明了它们在一系列图像、图形和点云实验中优于现有的集合学习架构。
E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
Harvard University(哈佛大学);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Robert Bosch Research and Technology Center(罗伯特·博世研究与技术中心);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);Massachusetts Institute of Technology(麻省理工学院)
Quantitative Approximation Rates for Group Equivariant Learning
Department of Mathematics(数学系);Texas A&M University(德克萨斯A&M大学);Faculty of Mathematics(数学系);Technion- Israel Institute of Technology(技术学院-以色列理工学院);Computer Science and Artificial Intelligence Laboratory(计算机科学与人工智能实验室);Massachusetts Institute of Technology(麻省理工学院)
Weisfeiler Leman for Euclidean Equivariant Machine Learning
Faculty of Mathematics, Technion - Israel Institute of Technology(以色列理工学院数学学院);Faculty of Computer Science, Technion - Israel Institute of Technology(以色列理工学院计算机科学学院)
University of Kansas(堪萨斯大学);Polytechnic University of Catalonia(加泰罗尼亚理工大学);Indian Institute of Technology Bhilai(比莱印度理工学院);University of Florida(佛罗里达大学);University of Alabama(阿拉巴马大学);Software Engineering Institute, Carnegie Mellon University(卡内基梅隆大学软件工程研究所)
eCP: Equivariant Conformal Prediction with pre-trained models
GRASP Laboratory, Department of Electrical & Systems Engineering, University of Pennsylvania(宾夕法尼亚大学电气与系统工程系GRASP实验室);Department of Computer Science, University of Southern California(南加州大学计算机科学系);Automatic Control Laboratory, ETH Zürich(苏黎世联邦理工学院自动控制实验室)