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

May 26, 2023

D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Bias
Sabit Hassan, Malihe Alikhani
Active Learning Bias Mitigation NLP Model Mitigating Bias Annotation System Clustering Based Active Learning

May 24, 2023

Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization
Feifei Shao, Yawei Luo, Lei Chen, Ping Liu, Wei Yang, Yi Yang, Jun Xiao
Bias Mitigation Weakly Supervised Object Localization Counterfactual Learning Counterfactual Representation

May 23, 2023

FITNESS: A Causal De-correlation Approach for Mitigating Bias in Machine Learning Software
Ying Xiao, Shangwen Wang, Sicen Liu, Dingyuan Xue, Xian Zhan, Yepang Liu
Bias Mitigation Mitigating Bias Biased Datasets Physical Activity Causal Approach Fairness Performance Trade Machine Learning Software

May 22, 2023

Fairness of ChatGPT
Yunqi Li, Lanjing Zhang, Yongfeng Zhang
ChatGPT Generated Conversation Procedural Fairness Bias Mitigation Group Fairness Fairness Evaluation Fairness Performance

May 11, 2023

Data quality dimensions for fair AI
Camilla Quaresmini, Giuseppe Primiero
Absolute Stance Bias Bias Mitigation Data Quality Discriminative Reply Gender Classification Fair AI

May 9, 2023

ChatGPT as a Text Simplification Tool to Remove Bias
Charmaine Barker, Dimitar Kazakov
Language Model ChatGPT Generated Conversation Absolute Stance Bias Bias Mitigation Text Simplification Linguistic Signal

April 12, 2023

Auditing ICU Readmission Rates in an Clinical Database: An Analysis of Risk Factors and Clinical Outcomes
Shaina Raza
Machine Learning General Analysis Bias Mitigation Risk Factor Clinical Outcome Fairness Audit Data Classification

March 20, 2023

Bias mitigation techniques in image classification: fair machine learning in human heritage collections
Dalia Ortiz Pablo, Sushruth Badri, Erik Norén, Christoph Nötzli
Transfer Learning Image Classification Bias Mitigation Fair Machine Learning Face Dataset

March 14, 2023

Variation of Gender Biases in Visual Recognition Models Before and After Finetuning
Jaspreet Ranjit, Tianlu Wang, Baishakhi Ray, Vicente Ordonez
Deep Learning Model Gender Bias Bias Mitigation Self Supervised Model Category Wise Variation Recognition Model Biased Association

March 8, 2023

Using Positive Matching Contrastive Loss with Facial Action Units to mitigate bias in Facial Expression Recognition
Varsha Suresh, Desmond C. Ong
Absolute Stance Bias Contrastive Loss Bias Mitigation Facial Expression Recognition Model Fairness Facial Action Unit Correlation Bias

February 22, 2023

Uncovering Bias in Face Generation Models
Cristian Muñoz, Sara Zannone, Umar Mohammed, Adriano Koshiyama
GAN Model Bias Mitigation Group Fairness Face Generation Feature Perturbation Bias Discovery

February 21, 2023

Managing multi-facet bias in collaborative filtering recommender systems
Samira Vaez Barenji, Saeed Farzi
Recommender System Bias Mitigation Recommendation Algorithm Traditional Recommender Multiple Bias

February 14, 2023

When mitigating bias is unfair: multiplicity and arbitrariness in algorithmic group fairness
Natasa Krco, Thibault Laugel, Vincent Grari, Jean-Michel Loubes, Marcin Detyniecki
Absolute Stance Bias Bias Mitigation Group Fairness Fair Machine Learning Model Multiplicity Algorithmic Arbitrariness

February 13, 2023

Parameter-efficient Modularised Bias Mitigation via AdapterFusion
Deepak Kumar, Oleg Lesota, George Zerveas, Daniel Cohen, Carsten Eickhoff, Markus Schedl, Navid Rekabsaz
Bias Mitigation Large Pre Trained Language Model

February 11, 2023

Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronouns
Zhongbin Xie, Vid Kocijan, Thomas Lukasiewicz, Oana-Maria Camburu
Gender Bias Bias Mitigation Coreference Resolution Filling Gap Counterfactual Generation Counterfactual Data Augmentation Binary Pronoun

January 31, 2023

Fairness-aware Vision Transformer via Debiased Self-Attention
Yao Qiang, Chengyin Li, Prashant Khanduri, Dongxiao Zhu
Vision Transformer Bias Mitigation Attention Regularization Attention Bias Exposure Fairness

January 30, 2023

How Far Can It Go?: On Intrinsic Gender Bias Mitigation for Text Classification
Ewoenam Tokpo, Pieter Delobelle, Bettina Berendt, Toon Calders
Text Classification Gender Bias Bias Mitigation Intrinsic Bias

January 8, 2023

Fair Multi-Exit Framework for Facial Attribute Classification
Ching-Hao Chiu, Hao-Wei Chung, Yu-Jen Chen, Yiyu Shi, Tsung-Yi Ho
Bias Mitigation Facial Attribute Fair AI Fairness Method Fairness Condition

December 26, 2022

Bias Mitigation Framework for Intersectional Subgroups in Neural Networks
Narine Kokhlikyan, Bilal Alsallakh, Fulton Wang, Vivek Miglani, Oliver Aobo Yang, David Adkins
Neural Network Bias Mitigation Fairness Constraint Fairness Aware Learning

November 20, 2022

Conceptor-Aided Debiasing of Large Language Models
Li S. Yifei, Lyle Ungar, João Sedoc
Large Language Model Bias Mitigation Debiasing Framework BERT Like