paper-with-me

홈 › Papers

Learning Fairer Representations with FairVIC

2024-04-28 · Charmaine Barker, Daniel Bethell, Dimitar Kazakov

Mitigating bias in automated decision-making systems, particularly in deep learning models, is a critical challenge due to nuanced definitions of fairness, dataset-specific biases, and the inherent trade-off between fairness and accuracy. To address these issues, we introduce FairVIC, an innovative approach that enhances fairness in neural networks by integrating variance, invariance, and covariance terms into the loss function during training. Unlike methods that rely on predefined fairness criteria, FairVIC abstracts fairness concepts to minimise dependency on protected characteristics. We evaluate FairVIC against comparable bias mitigation techniques on benchmark datasets, considering both group and individual fairness, and conduct an ablation study on the accuracy-fairness trade-off. FairVIC demonstrates significant improvements ($\approx70\%$) in fairness across all tested metrics without compromising accuracy, thus offering a robust, generalisable solution for fair deep learning across diverse tasks and datasets.

📄 PDF Abstract BibTeX arXiv:2404.18134

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDeep LearningFairness

Similar Papers 제목 키워드 기반

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs

2024-03-22 · Sepehr Dehdashtian, Lan Wang, Vishnu Naresh Boddeti

Large pre-trained vision-language models such as CLIP provide compact and general-purpose representations of text and images that are demonstrably effective across multiple downstream zero-shot prediction tasks. However,…

Fairness

Contrastive Learning for Fair Representations

2021-12-17 · ACL ARR December 2022 12 · Anonymous

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as…

AttributeClassificationContrastive LearningMulti-class Classification

Contrastive Learning for Fair Representations

2021-09-22 · Aili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin 외

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as…

AttributeContrastive Learning

Fairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification

2024-12-04 · Alexandre Fournier-Montgieux, Michael Soumm, Adrian Popescu, Bertrand Luvison 외

Face recognition and verification are two computer vision tasks whose performances have advanced with the introduction of deep representations. However, ethical, legal, and technical challenges due to the sensitive natur…

Face GenerationFace RecognitionFace VerificationFairness

Bigger Data or Fairer Data? Augmenting BERT via Active Sampling for Educational Text Classification

2022-10-01 · COLING 2022 10 · Lele Sha, Yuheng Li, Dragan Gasevic, Guanliang Chen

Pretrained Language Models (PLMs), though popular, have been diagnosed to encode bias against protected groups in the representations they learn, which may harm the prediction fairness of downstream models. Given that su…

Fairnesstext-classificationText Classification