SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.00876 · CVPR · 2025

Improve Representation for Imbalanced Regression through Geometric Constraints

Yichi Zhang, Yingtian Zou, Zijian Dong, Yilei Wu, Juan Zhou, Chongyao Chen

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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. Classificationbased 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 geometrybased loss functions. Code is available here.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2503.00876")
get_code_for_paper("2503.00876")
have("2503.00876")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2503.00876.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2503.00876.svg)](https://syntology.ai/paper/2503.00876)

Connect an agent — have() is free.