paper-with-me

홈 › Papers

An Attention-based Framework for Fair Contrastive Learning

2024-11-22 · Stefan K. Nielsen, Tan M. Nguyen

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.

📄 PDF Abstract BibTeX arXiv:2411.14765

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning

2024-10-23 · Wei Chen, Meng Yuan, Zhao Zhang, Ruobing Xie 외

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 Systems

FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning

2022-08-22 · Siyi Du, Ben Hers, Nourhan Bayasi, Ghassan Hamarneh 외

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+3

FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding

2023-11-27 · CVPR 2025 1 · Thanh-Dat Truong, Utsav Prabhu, Bhiksha Raj, Jackson Cothren 외

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+2

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

Fair Node Representation Learning via Adaptive Data Augmentation

2022-01-21 · O. Deniz Kose, Yanning Shen

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