paper-with-me

홈 › Papers

Symmetry From Scratch: Group Equivariance as a Supervised Learning Task

2024-10-05 · Haozhe Huang, Leo Kaixuan Cheng, Kaiwen Chen, Alán Aspuru-Guzik

In machine learning datasets with symmetries, the paradigm for backward compatibility with symmetry-breaking has been to relax equivariant architectural constraints, engineering extra weights to differentiate symmetries of interest. However, this process becomes increasingly over-engineered as models are geared towards specific symmetries/asymmetries hardwired of a particular set of equivariant basis functions. In this work, we introduce symmetry-cloning, a method for inducing equivariance in machine learning models. We show that general machine learning architectures (i.e., MLPs) can learn symmetries directly as a supervised learning task from group equivariant architectures and retain/break the learned symmetry for downstream tasks. This simple formulation enables machine learning models with group-agnostic architectures to capture the inductive bias of group-equivariant architectures.

📄 PDF Abstract BibTeX arXiv:2410.03989

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive Bias

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Approximation-Generalization Trade-offs under (Approximate) Group Equivariance

2023-05-27 · NeurIPS 2023 11 · Mircea Petrache, Shubhendu Trivedi

The explicit incorporation of task-specific inductive biases through symmetry has emerged as a general design precept in the development of high-performance machine learning models. For example, group equivariant neural …

Drug Design

Learning Layer-wise Equivariances Automatically using Gradients

2023-09-21 · NeurIPS 2023 11

Convolutions encode equivariance symmetries into neural networks leading to better generalisation performance. However, symmetries provide fixed hard constraints on the functions a network can represent, need to be speci…

Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts

2024-07-05 · Hyunsu Kim, Yegon Kim, Hongseok Yang, Juho Lee

Group Equivariant CNNs (G-CNNs) have shown promising efficacy in various tasks, owing to their ability to capture hierarchical features in an equivariant manner. However, their equivariance is fixed to the symmetry of th…

Variational Inference

Approximate Equivariance in Reinforcement Learning

2024-11-06 · Jung Yeon Park, Sujay Bhatt, Sihan Zeng, Lawson L. S. Wong 외

Equivariant neural networks have shown great success in reinforcement learning, improving sample efficiency and generalization when there is symmetry in the task. However, in many problems, only approximate symmetry is p…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1

Learning finite symmetry groups of dynamical systems via equivariance detection

2025-03-04 · Pablo Calvo-Barlés, Sergio G. Rodrigo, Luis Martín-Moreno

In this work, we introduce the Equivariance Seeker Model (ESM), a data-driven method for discovering the underlying finite equivariant symmetry group of an arbitrary function. ESM achieves this by optimizing a loss funct…