Balancing out Bias: Achieving Fairness Through Balanced Training
Bias in natural language processing manifests as disparities in error rates across author demographics, typically disadvantaging minority groups. Although dataset balancing has been shown to be effective in mitigating bias, existing approaches do not directly account for correlations between author demographics and linguistic variables. To achieve Equal Opportunity fairness, this paper introduces a simple but highly effective objective for countering bias using balanced training. We extend the method in the form of a gated model, which incorporates protected attributes as input, and show that it is effective at reducing bias in predictions through demographic input perturbation, outperforming all other bias mitigation techniques when combined with balanced training.
Code (0)
등록된 구현이 없습니다.
Tasks
FairnessSimilar Papers 제목 키워드 기반
Balancing out Bias: Achieving Fairness Through Balanced Training
Group bias in natural language processing tasks manifests as disparities in system error rates across texts authorized by different demographic groups, typically disadvantaging minority groups. Dataset balancing has been…
FairnessFair GANs through model rebalancing for extremely imbalanced class distributions
Deep generative models require large amounts of training data. This often poses a problem as the collection of datasets can be expensive and difficult, in particular datasets that are representative of the appropriate un…
FairnessGenerative Adversarial NetworkFairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification
Face gender classification models often reflect and amplify demographic biases present in their training data, leading to uneven performance across gender and racial subgroups. We introduce pseudo-balancing, a simple and…
Achieving Fair Skin Lesion Detection through Skin Tone Normalization and Channel Pruning
Recent works have shown that deep learning based skin lesion image classification models trained on unbalanced dataset can exhibit bias toward protected demographic attributes such as race, age,and gender. Current bias m…
Image ClassificationData AugmentationBalancing the Scales: Reinforcement Learning for Fair Classification
Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent trends favor algorithmic methods that embed fairness into the training process. These methods steer model…
ClassificationFairnessimbalanced classificationreinforcement-learning+2