Learning Fairer Representations with FairVIC
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingDeep LearningFairnessSimilar Papers 제목 키워드 기반
FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
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,…
FairnessContrastive Learning for Fair Representations
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 ClassificationContrastive Learning for Fair Representations
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 LearningFairer Analysis and Demographically Balanced Face Generation for Fairer Face Verification
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 VerificationFairnessBigger Data or Fairer Data? Augmenting BERT via Active Sampling for Educational Text Classification
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