paper-with-me

홈 › Papers

Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets

2026-05-11 · Thuan Nguyen, Shuchin Aeron, D. Richard Brown, Prakash Ishwar arxiv

In this paper, we provide a computable characterization of the geometry of optimal representations in Contrastive Learning (CL) when the classes are imbalanced. When classes are balanced and the representation dimension is greater than the number of classes, it is well-known that the optimal representations exhibit Neural Collapse (NC), i.e., representations from the same class collapse to their class means and the class means form an Equiangular Tight Frame (ETF). For imbalanced classes and a large, generalized family of CL losses, we prove that the optimal representations of all samples from the same class collapse to their class means and their geometry exhibits an angular symmetry structure that is determined by the relative class proportions. In general, we show that the geometry can be determined by solving a convex optimization problem. Exploiting this symmetry structure, we analytically investigate a special case where class imbalance is extreme and prove that CL exhibits a phenomenon called Minority Collapse (MC) where all samples from the minority classes (classes with small probabilities) collapse into a single vector, whenever the class imbalance exceeds a threshold, which in turn depends on the regularity properties of the CL loss used and on the number of negative samples. Numerical results are provided to illustrate these phenomena and corroborate the theoretical results. We conclude by identifying a number of open problems.

📄 PDF Abstract BibTeX arXiv:2605.11291

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

Cluster-guided Contrastive Class-imbalanced Graph Classification

2024-12-17 · Wei Ju, Zhengyang Mao, Siyu Yi, Yifang Qin 외

This paper studies the problem of class-imbalanced graph classification, which aims at effectively classifying the graph categories in scenarios with imbalanced class distributions. While graph neural networks (GNNs) hav…

ClassificationContrastive LearningGraph Classification

Contrastive Attraction and Contrastive Repulsion for Representation Learning

2021-05-08 · Huangjie Zheng, Xu Chen, Jiangchao Yao, Hongxia Yang 외

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entro…

Contrastive LearningRepresentation Learning

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery

2025-04-02 · Shijie Ma, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu

Generalized category discovery (GCD) is a pragmatic but underexplored problem, which requires models to automatically cluster and discover novel categories by leveraging the labeled samples from old classes. The challeng…

Contrastive Learning

CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learning

2023-12-15 · Bowen Tao, Lan Li, Xin-Chun Li, De-Chuan Zhan

Due to the advantages of leveraging unlabeled data and learning meaningful representations, semi-supervised learning and contrastive learning have been progressively combined to achieve better performances in popular app…

Contrastive Learningimage-classificationImage Classification

SC-MIL: Supervised Contrastive Multiple Instance Learning for Imbalanced Classification in Pathology

2023-03-23 · Dinkar Juyal, Siddhant Shingi, Syed Ashar Javed, Harshith Padigela 외

Multiple Instance learning (MIL) models have been extensively used in pathology to predict biomarkers and risk-stratify patients from gigapixel-sized images. Machine learning problems in medical imaging often deal with r…

Contrastive Learningimbalanced classificationMultiple Instance Learning