Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeContrastive LearningFairnessRepresentation LearningSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Conditional Supervised Contrastive Learning for Fair Text Classification
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+2ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs
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 LearningDualFair: Fair Representation Learning at Both Group and Individual Levels via Contrastive Self-supervision
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+1FairContrast: Enhancing Fairness through Contrastive learning and Customized Augmenting Methods on Tabular Data
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 LearningEvaluating the fairness of fine-tuning strategies in self-supervised learning
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