Saved in:
Bibliographic Details
Main Authors: Dong, Zijian, Wu, Yilei, Chen, Chongyao, Zou, Yingtian, Zhang, Yichi, Zhou, Juan Helen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.00876
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909520565895168
author Dong, Zijian
Wu, Yilei
Chen, Chongyao
Zou, Yingtian
Zhang, Yichi
Zhou, Juan Helen
author_facet Dong, Zijian
Wu, Yilei
Chen, Chongyao
Zou, Yingtian
Zhang, Yichi
Zhou, Juan Helen
contents In representation learning, uniformity refers to the uniform feature distribution in the latent space (i.e., unit hypersphere). Previous work has shown that improving uniformity contributes to the learning of under-represented classes. However, most of the previous work focused on classification; the representation space of imbalanced regression remains unexplored. Classification-based methods are not suitable for regression tasks because they cluster features into distinct groups without considering the continuous and ordered nature essential for regression. In a geometric aspect, we uniquely focus on ensuring uniformity in the latent space for imbalanced regression through two key losses: enveloping and homogeneity. The enveloping loss encourages the induced trace to uniformly occupy the surface of a hypersphere, while the homogeneity loss ensures smoothness, with representations evenly spaced at consistent intervals. Our method integrates these geometric principles into the data representations via a Surrogate-driven Representation Learning (SRL) framework. Experiments with real-world regression and operator learning tasks highlight the importance of uniformity in imbalanced regression and validate the efficacy of our geometry-based loss functions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improve Representation for Imbalanced Regression through Geometric Constraints
Dong, Zijian
Wu, Yilei
Chen, Chongyao
Zou, Yingtian
Zhang, Yichi
Zhou, Juan Helen
Machine Learning
In representation learning, uniformity refers to the uniform feature distribution in the latent space (i.e., unit hypersphere). Previous work has shown that improving uniformity contributes to the learning of under-represented classes. However, most of the previous work focused on classification; the representation space of imbalanced regression remains unexplored. Classification-based methods are not suitable for regression tasks because they cluster features into distinct groups without considering the continuous and ordered nature essential for regression. In a geometric aspect, we uniquely focus on ensuring uniformity in the latent space for imbalanced regression through two key losses: enveloping and homogeneity. The enveloping loss encourages the induced trace to uniformly occupy the surface of a hypersphere, while the homogeneity loss ensures smoothness, with representations evenly spaced at consistent intervals. Our method integrates these geometric principles into the data representations via a Surrogate-driven Representation Learning (SRL) framework. Experiments with real-world regression and operator learning tasks highlight the importance of uniformity in imbalanced regression and validate the efficacy of our geometry-based loss functions.
title Improve Representation for Imbalanced Regression through Geometric Constraints
topic Machine Learning
url https://arxiv.org/abs/2503.00876