Learning Symmetrization for Equivariance with Orbit Distance Minimization
We present a general framework for symmetrizing an arbitrary neural-network architecture and making it equivariant with respect to a given group. We build upon the proposals of Kim et al. (2023); Kaba et al. (2023) for symmetrization, and improve them by replacing their conversion of neural features into group representations, with an optimization whose loss intuitively measures the distance between group orbits. This change makes our approach applicable to a broader range of matrix groups, such as the Lorentz group O(1, 3), than these two proposals. We experimentally show our method's competitiveness on the SO(2) image classification task, and also its increased generality on the task with O(1, 3). Our implementation will be made accessible at https://github.com/tiendatnguyen-vision/Orbit-symmetrize.
Code (1)
Tasks
image-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Equivariance and Augmentation for Bayesian Neural Networks
Symmetries are important for many deep learning tasks, ranging from applications in the sciences to medical imaging. However, there is an ongoing debate about whether to impose symmetry constraints on the neural network …
Data AugmentationOrbit-Equivariant Graph Neural Networks
Equivariance is an important structural property that is captured by architectures such as graph neural networks (GNNs). However, equivariant graph functions cannot produce different outputs for similar nodes, which may …
Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries. In contrary to equivariant architectures, we use an arbitrary base model such as an MLP o…
Graph ClassificationGraph RegressionLink PredictionAccurate and Fast Retrieval for Complex Non-metric Data via Neighborhood Graphs
We demonstrate that a graph-based search algorithm-relying on the construction of an approximate neighborhood graph-can directly work with challenging non-metric and/or non-symmetric distances without resorting to metric…
graph constructionRetrievalSymmetry-Protected Lyapunov Neutral Modes in Equivariant Recurrent Networks
Recurrent networks that store position, phase, or other continuous variables need state-space directions that remain neutral over long horizons. We give a symmetry-based account of when such neutral directions are guaran…