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

September 24, 2024

Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs
Amartya Roy, Danush Khanna, Devanshu Mahapatra, Vasanthakumar, Avirup Das, Kripabandhu Ghosh
Medical LLM Bias Mitigation Social Bias Self Debiasing

September 20, 2024

September 16, 2024

Toward Mitigating Sex Bias in Pilot Trainees' Stress and Fatigue Modeling
Rachel Pfeifer, Sudip Vhaduri, Mark Wilson, Julius Keller
Gender Bias Bias Mitigation Continuous Chronic Stress Equalized Odds Mercedes Benz Drive Pilot Fatigue Life Prediction Muscle Fatigue

September 15, 2024

Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models
Sahil Kuchlous, Marvin Li, Jeffrey G. Wang
Diffusion Model Global Impact Text to Image Bias Mitigation Multimodal Embeddings Bias Challenge

September 8, 2024

Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study
Emmanouil Panagiotou, Arjun Roy, Eirini Ntoutsi
Comparative Study Procedural Fairness Class Imbalance Bias Mitigation Group Imbalance Synthetic Tabular Data Generation

September 7, 2024

Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation
Lars Nieradzik, Henrike Stephani, Janis Keuper
Convolutional Neural Network Native Robustness Inherent Interpretability CNN Model Bias Mitigation Object Localization Filling Gap Shape Prior Salient Region

September 6, 2024

AGR: Age Group fairness Reward for Bias Mitigation in LLMs
Shuirong Cao, Ruoxi Cheng, Zhiqiang Wang
Medical LLM Bias Mitigation Individual Fairness Demographic Bias Fair Incentive

August 28, 2024

August 27, 2024

August 22, 2024

Aligning (Medical) LLMs for (Counterfactual) Fairness
Raphael Poulain, Hamed Fayyaz, Rahmatollah Beheshti
Large Language Model Procedural Fairness Alignment Problem Bias Mitigation Model Alignment

August 21, 2024

BAdd: Bias Mitigation through Bias Addition
Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Bias Mitigation Fair Representation Computer Vision Datasets Latent Bias

August 19, 2024

Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems
Zhirong Huang, Shichao Zhang, Debo Cheng, Jiuyong Li, Lin Liu, Guixian Zhang
Recommender System Bias Mitigation Popularity Bias Debiased Contrastive Conformity Bias

August 10, 2024

MABR: A Multilayer Adversarial Bias Removal Approach Without Prior Bias Knowledge
Maxwell J. Yin, Boyu Wang, Charles Ling
Gender Bias Bias Mitigation Social Bias Prior Knowledge Biased Feature Adversarial Bias

August 7, 2024

Editable Fairness: Fine-Grained Bias Mitigation in Language Models
Ruizhe Chen, Yichen Li, Jianfei Yang, Joey Tianyi Zhou, Zuozhu Liu
Large Language Model Language Model Bias Mitigation Fairness Improvement Data Debiasing Fine Grained Bias

August 5, 2024

Fairness and Bias Mitigation in Computer Vision: A Survey
Sepehr Dehdashtian, Ruozhen He, Yi Li, Guha Balakrishnan, Nuno Vasconcelos, Vicente Ordonez, Vishnu Naresh Boddeti
Timely Survey Generative Model Computer Vision Procedural Fairness Bias Mitigation Vision System Multimodal Foundation

July 30, 2024

On Biases in a UK Biobank-based Retinal Image Classification Model
Anissa Alloula, Rima Mustafa, Daniel R McGowan, Bartłomiej W. Papież
Bias Mitigation Fundus Image Topic Bias Disease Classification Significant Disparity

July 24, 2024

Looking at Model Debiasing through the Lens of Anomaly Detection
Vito Paolo Pastore, Massimiliano Ciranni, Davide Marinelli, Francesca Odone, Vittorio Murino
Anomaly Detection Camera Lens Bias Mitigation Bias Detection Model Debiasing Bias Aligned Sample

Bias Mitigation

Papers

Do the Right Thing, Just Debias! Multi-Category Bias Mitigation Using LLMs

A Multi-LLM Debiasing Framework

STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions

Toward Mitigating Sex Bias in Pilot Trainees' Stress and Fatigue Modeling

Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models

Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study

Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation

AGR: Age Group fairness Reward for Bias Mitigation in LLMs

Using Backbone Foundation Model for Evaluating Fairness in Chest Radiography Without Demographic Data

Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems

Examining the Interplay Between Privacy and Fairness for Speech Processing: A Review and Perspective

Ensuring Equitable Financial Decisions: Leveraging Counterfactual Fairness and Deep Learning for Bias

Aligning (Medical) LLMs for (Counterfactual) Fairness

BAdd: Bias Mitigation through Bias Addition

Debiased Contrastive Representation Learning for Mitigating Dual Biases in Recommender Systems

MABR: A Multilayer Adversarial Bias Removal Approach Without Prior Bias Knowledge

Editable Fairness: Fine-Grained Bias Mitigation in Language Models

Fairness and Bias Mitigation in Computer Vision: A Survey

On Biases in a UK Biobank-based Retinal Image Classification Model

Looking at Model Debiasing through the Lens of Anomaly Detection