Bias Mitigation

Bias mitigation in machine learning aims to create fairer and more equitable algorithms by addressing biases stemming from training data and model architectures. Current research focuses on developing and evaluating various bias mitigation techniques, including data augmentation strategies (like mixup and proximity sampling), adversarial training methods, and post-processing approaches such as channel pruning and dropout. These efforts span diverse applications, from computer vision and natural language processing to medical image analysis and recommender systems, highlighting the broad significance of this field for ensuring responsible and ethical AI development. The ultimate goal is to improve model fairness without sacrificing accuracy or utility, leading to more equitable outcomes across different demographic groups.

Papers

October 18, 2023

October 13, 2023

Mitigating Bias for Question Answering Models by Tracking Bias Influence
Mingyu Derek Ma, Jiun-Yu Kao, Arpit Gupta, Yu-Hsiang Lin, Wenbo Zhao, Tagyoung Chung, Wei Wang, Kai-Wei Chang, Nanyun Peng
Bias Mitigation Mitigating Bias Question Answering Model Bias Metric

September 22, 2023

FairComp: Workshop on Fairness and Robustness in Machine Learning for Ubiquitous Computing
Sofia Yfantidou, Dimitris Spathis, Marios Constantinides, Tong Xia, Niels van Berkel
Machine Learning Native Robustness Procedural Fairness Bias Mitigation Pervasive Computing

September 7, 2023

Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate
Yuancheng Xu, Chenghao Deng, Yanchao Sun, Ruijie Zheng, Xiyao Wang, Jieyu Zhao, Furong Huang
Long Term Bias Mitigation Sequential Decision Long Term Fairness Fairness Criterion

August 23, 2023

Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD
Moritz Knolle, Robert Dorfman, Alexander Ziller, Daniel Rueckert, Georgios Kaissis
Human Understanding Bias Mitigation Estimation Bias Private Gradient Gradient Oracle

August 22, 2023

August 19, 2023

Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts
Jiaxuan Li, Duc Minh Vo, Hideki Nakayama
Mixture Component Bias Mitigation Bias Removal Bias Reduction Space Bias Based Debiasing

August 9, 2023

Are Sex-based Physiological Differences the Cause of Gender Bias for Chest X-ray Diagnosis?
Nina Weng, Siavash Bigdeli, Eike Petersen, Aasa Feragen
Gender Bias Bias Mitigation Actual Cause Chest Radiograph Gender Difference

July 19, 2023

Can Instruction Fine-Tuned Language Models Identify Social Bias through Prompting?
Omkar Dige, Jacob-Junqi Tian, David Emerson, Faiza Khan Khattak
Bias Mitigation Social Bias Fine Tuned Language Model Instruction Tuned Language Model Zero Shot Prompting Language Model Application Bias Related Task

July 13, 2023

National Origin Discrimination in Deep-learning-powered Automated Resume Screening
Sihang Li, Kuangzheng Li, Haibing Lu
Artificial Intelligence Bias Mitigation AI Tool Resume Job Nationality Bias Resume Screening

July 9, 2023

Towards Assumption-free Bias Mitigation
Chia-Yuan Chang, Yu-Neng Chuang, Kwei-Herng Lai, Xiaotian Han, Xia Hu, Na Zou
Bias Mitigation Sensitive Attribute Biased Prediction

June 15, 2023

Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML
Giang Nguyen, Sumon Biswas, Hridesh Rajan
Machine Learning Bias Mitigation Online autoML Fair Machine Learning Fairness Improvement Accuracy Loss Bias Mitigation Algorithm

June 6, 2023

An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models
Zhongbin Xie, Thomas Lukasiewicz
Language Model Bias Mitigation Parameter Efficient Empirical Analysis Human Bias Counterfactual Data Augmentation

May 31, 2023

Bias Mitigation Methods for Binary Classification Decision-Making Systems: Survey and Recommendations
Madeleine Waller, Odinaldo Rodrigues, Oana Cocarascu
Timely Survey Bias Mitigation Movie Recommendation Binary Classification Fair Machine Learning Decision Making System

May 28, 2023

Robust Natural Language Understanding with Residual Attention Debiasing
Fei Wang, James Y. Huang, Tianyi Yan, Wenxuan Zhou, Muhao Chen
Bias Mitigation Attention Bias Based Debiasing Robust Natural Language Understanding

Bias Mitigation

Papers

Fairer and More Accurate Tabular Models Through NAS

A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation

Mitigating Bias for Question Answering Models by Tracking Bias Influence

FairComp: Workshop on Fairness and Robustness in Machine Learning for Ubiquitous Computing

Data Augmentation via Subgroup Mixup for Improving Fairness

Mitigating Group Bias in Federated Learning for Heterogeneous Devices

Bayesian uncertainty-weighted loss for improved generalisability on polyp segmentation task

Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate

Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD

Targeted Data Augmentation for bias mitigation

Test Time Embedding Normalization for Popularity Bias Mitigation

Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts

Are Sex-based Physiological Differences the Cause of Gender Bias for Chest X-ray Diagnosis?

Can Instruction Fine-Tuned Language Models Identify Social Bias through Prompting?

National Origin Discrimination in Deep-learning-powered Automated Resume Screening

Towards Assumption-free Bias Mitigation

Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML

An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models

Bias Mitigation Methods for Binary Classification Decision-Making Systems: Survey and Recommendations

Robust Natural Language Understanding with Residual Attention Debiasing