BriefGPT.xyz
Oct, 2024
从零开始的对称性：群等变性作为监督学习任务
Symmetry From Scratch: Group Equivariance as a Supervised Learning Task
HTML
PDF
Haozhe Huang, Leo Kaixuan Cheng, Kaiwen Chen, Alán Aspuru-Guzik
TL;DR
该研究针对机器学习模型在面对对称性时的局限性，提出了一种名为对称克隆的方法，以在通用机器学习架构中引入等变性。通过这一新方法，模型能够直接学习对称性，并在后续任务中保留或打破这种对称性，极大地提升了群不变架构的学习能力。
Abstract
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 sym
→