Improving Equivariant Model Training via Constraint Relaxation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pertigkiozoglou, Stefanos, Chatzipantazis, Evangelos, Trivedi, Shubhendu, Daniilidis, Kostas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929656718950400
author Pertigkiozoglou, Stefanos
Chatzipantazis, Evangelos
Trivedi, Shubhendu
Daniilidis, Kostas
author_facet Pertigkiozoglou, Stefanos
Chatzipantazis, Evangelos
Trivedi, Shubhendu
Daniilidis, Kostas
contents Equivariant neural networks have been widely used in a variety of applications due to their ability to generalize well in tasks where the underlying data symmetries are known. Despite their successes, such networks can be difficult to optimize and require careful hyperparameter tuning to train successfully. In this work, we propose a novel framework for improving the optimization of such models by relaxing the hard equivariance constraint during training: We relax the equivariance constraint of the network's intermediate layers by introducing an additional non-equivariant term that we progressively constrain until we arrive at an equivariant solution. By controlling the magnitude of the activation of the additional relaxation term, we allow the model to optimize over a larger hypothesis space containing approximate equivariant networks and converge back to an equivariant solution at the end of training. We provide experimental results on different state-of-the-art network architectures, demonstrating how this training framework can result in equivariant models with improved generalization performance. Our code is available at https://github.com/StefanosPert/Equivariant_Optimization_CR
format Preprint
id arxiv_https___arxiv_org_abs_2408_13242
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Equivariant Model Training via Constraint Relaxation
Pertigkiozoglou, Stefanos
Chatzipantazis, Evangelos
Trivedi, Shubhendu
Daniilidis, Kostas
Machine Learning
Equivariant neural networks have been widely used in a variety of applications due to their ability to generalize well in tasks where the underlying data symmetries are known. Despite their successes, such networks can be difficult to optimize and require careful hyperparameter tuning to train successfully. In this work, we propose a novel framework for improving the optimization of such models by relaxing the hard equivariance constraint during training: We relax the equivariance constraint of the network's intermediate layers by introducing an additional non-equivariant term that we progressively constrain until we arrive at an equivariant solution. By controlling the magnitude of the activation of the additional relaxation term, we allow the model to optimize over a larger hypothesis space containing approximate equivariant networks and converge back to an equivariant solution at the end of training. We provide experimental results on different state-of-the-art network architectures, demonstrating how this training framework can result in equivariant models with improved generalization performance. Our code is available at https://github.com/StefanosPert/Equivariant_Optimization_CR
title Improving Equivariant Model Training via Constraint Relaxation
topic Machine Learning
url https://arxiv.org/abs/2408.13242