An Attention-based Framework for Fair Contrastive Learning
Contrastive learning has proven instrumental in learning unbiased representations of data, especially in complex environments characterized by high-cardinality and high-dimensional sensitive information. However, existing approaches within this setting require predefined modelling assumptions of bias-causing interactions that limit the model's ability to learn debiased representations. In this work, we propose a new method for fair contrastive learning that employs an attention mechanism to model bias-causing interactions, enabling the learning of a fairer and semantically richer embedding space. In particular, our attention mechanism avoids bias-causing samples that confound the model and focuses on bias-reducing samples that help learn semantically meaningful representations. We verify the advantages of our method against existing baselines in fair contrastive learning and show that our approach can significantly boost bias removal from learned representations without compromising downstream accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning
As trustworthy AI continues to advance, the fairness issue in recommendations has received increasing attention. A recommender system is considered unfair when it produces unequal outcomes for different user groups based…
Contrastive LearningData AugmentationFairnessRecommendation SystemsFairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning
Deep learning models have achieved great success in automating skin lesion diagnosis. However, the ethnic disparity in these models' predictions, where lesions on darker skin types are usually underrepresented and have l…
AttributeContrastive LearningDeep LearningDisentanglement+3FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic fo…
Continual LearningContinual Semantic SegmentationFairnessScene Segmentation+2Conditional 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+2Fair Node Representation Learning via Adaptive Data Augmentation
Node representation learning has demonstrated its efficacy for various applications on graphs, which leads to increasing attention towards the area. However, fairness is a largely under-explored territory within the fiel…
Contrastive LearningData AugmentationFairnessLink Prediction+2