paper-with-me

Papers

Balancing out Bias: Achieving Fairness Through Balanced Training

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

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Fairness

Similar Papers 제목 키워드 기반

Balancing out Bias: Achieving Fairness Through Balanced Training

2021-09-16 · Xudong Han, Timothy Baldwin, Trevor Cohn

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…

Fairness

Fair GANs through model rebalancing for extremely imbalanced class distributions

2023-08-16 · Anubhav Jain, Nasir Memon, Julian Togelius

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 Network

Fairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification

2025-10-11 · Haohua Dong, Ana Manzano Rodríguez, Camille Guinaudeau, Shin'ichi Satoh arxiv

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

2025-09-24 · Zihan Wei, Tapabrata Chakraborti arxiv

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 Augmentation

Balancing the Scales: Reinforcement Learning for Fair Classification

2024-07-15 · Leon Eshuijs, Shihan Wang, Antske Fokkens

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