潜在対称性を持つ領域における同変モデルの意外な有効性
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
入力に現れない潜在的な対称性を持つロボット操作・制御タスクにおいて、厳密に一致しない同変制約を課すことが学習を助け、非同変手法より大幅に性能が向上することを示した研究。
著者: Dian Wang, Jung Yeon Park, Neel Sortur, Lawson L. S. Wong, Robin Walters, Robert Platt
分類: cs.LG, cs.RO
原文アブストラクト
Extensive work has demonstrated that equivariant neural networks can significantly improve sample efficiency and generalization by enforcing an inductive bias in the network architecture. These applications typically assume that the domain symmetry is fully described by explicit transformations of the model inputs and outputs. However, many real-life applications contain only latent or partial symmetries which cannot be easily described by simple transformations of the input. In these cases, it is necessary to learn symmetry in the environment instead of imposing it mathematically on the network architecture. We discover, surprisingly, that imposing equivariance constraints that do not exactly match the domain symmetry is very helpful in learning the true symmetry in the environment. We differentiate between extrinsic and incorrect symmetry constraints and show that while imposing incorrect symmetry can impede the model's performance, imposing extrinsic symmetry can actually improve performance. We demonstrate that an equivariant model can significantly outperform non-equivariant methods on domains with latent symmetries both in supervised learning and in reinforcement learning for robotic manipulation and control problems.
