paper-with-me

Papers

Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning

2021-06-05 · Martin Q. Ma, Yao-Hung Hubert Tsai, Paul Pu Liang, Han Zhao, Kun Zhang, Ruslan Salakhutdinov, Louis-Philippe Morency

Contrastive self-supervised learning (SSL) learns an embedding space that maps similar data pairs closer and dissimilar data pairs farther apart. Despite its success, one issue has been overlooked: the fairness aspect of representations learned using contrastive SSL. Without mitigation, contrastive SSL techniques can incorporate sensitive information such as gender or race and cause potentially unfair predictions on downstream tasks. In this paper, we propose a Conditional Contrastive Learning (CCL) approach to improve the fairness of contrastive SSL methods. Our approach samples positive and negative pairs from distributions conditioning on the sensitive attribute, or empirically speaking, sampling positive and negative pairs from the same gender or the same race. We show that our approach provably maximizes the conditional mutual information between the learned representations of the positive pairs, and reduces the effect of the sensitive attribute by taking it as the conditional variable. On seven fairness and vision datasets, we empirically demonstrate that the proposed approach achieves state-of-the-art downstream performances compared to unsupervised baselines and significantly improves the fairness of contrastive SSL models on multiple fairness metrics.

📄 PDF Abstract BibTeX arXiv:2106.02866

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeContrastive LearningFairnessRepresentation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
InfoNCE 설명 없음

Similar Papers 제목 키워드 기반

Conditional Supervised Contrastive Learning for Fair Text Classification

2022-05-23 · Jianfeng Chi, William Shand, Yaodong Yu, Kai-Wei Chang 외

Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data. However, the learned representations could potentially lead t…

ClassificationContrastive LearningFairnessRepresentation Learning+2

ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs

2026-05-03 · Marah Halawa, Olaf Hellwich arxiv

Self-supervised learning methods learn high-quality visual representations, yet recent studies show that these representations often capture demographic biases present in the training data. Existing fairness-aware method…

Self-Supervised LearningContrastive Learning

DualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision

2023-03-15 · Sungwon Han, Seungeon Lee, Fangzhao Wu, Sundong Kim 외

Algorithmic fairness has become an important machine learning problem, especially for mission-critical Web applications. This work presents a self-supervised model, called DualFair, that can debias sensitive attributes l…

counterfactualFairnessKnowledge DistillationRepresentation Learning+1

FairContrast: Enhancing Fairness through Contrastive learning and Customized Augmenting Methods on Tabular Data

2025-10-02 · Aida Tayebi, Ali Khodabandeh Yalabadi, Mehdi Yazdani-Jahromi, Ozlem Ozmen Garibay arxiv

As AI systems become more embedded in everyday life, the development of fair and unbiased models becomes more critical. Considering the social impact of AI systems is not merely a technical challenge but a moral imperati…

Representation LearningContrastive Learning

Evaluating the fairness of fine-tuning strategies in self-supervised learning

2021-10-01 · Jason Ramapuram, Dan Busbridge, Russ Webb

In this work we examine how fine-tuning impacts the fairness of contrastive Self-Supervised Learning (SSL) models. Our findings indicate that Batch Normalization (BN) statistics play a crucial role, and that updating onl…

FairnessSelf-Supervised Learning