Fairness Mitigation

Fairness mitigation in machine learning aims to develop algorithms and techniques that prevent discriminatory outcomes against protected groups, ensuring equitable treatment across different populations. Current research focuses on developing both pre-processing and post-processing methods, including adversarial perturbations on latent embeddings and multi-objective optimization techniques, to improve fairness while maintaining model accuracy. These efforts are crucial for building trustworthy AI systems and addressing ethical concerns in various applications, from healthcare and finance to social media, where biased models can have significant societal impacts. The field is actively exploring the interplay between fairness, privacy, and model utility, seeking to find optimal trade-offs among these competing objectives.

Papers

March 8, 2024

APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation
Zikang Xu, Fenghe Tang, Quan Quan, Qingsong Yao, S. Kevin Zhou
Deep Learning Intermediate Latent Fairness Aware Fairness Mitigation Hidden Representation Perturbation

February 6, 2024

Measuring machine learning harms from stereotypes: requires understanding who is being harmed by which errors in what ways
Angelina Wang, Xuechunzi Bai, Solon Barocas, Su Lin Blodgett
New Machine Human Understanding Error Feedback Stereotype Content Potential Harm Stereotypical Bias Gender Stereotype Fairness Mitigation

December 5, 2023

FRAPPE: A Group Fairness Framework for Post-Processing Everything
Alexandru Tifrea, Preethi Lahoti, Ben Packer, Yoni Halpern, Ahmad Beirami, Flavien Prost
Group Fairness Post Processing Fairness Accuracy Fairness Mitigation

February 17, 2023

Learning with Impartiality to Walk on the Pareto Frontier of Fairness, Privacy, and Utility
Mohammad Yaghini, Patty Liu, Franziska Boenisch, Nicolas Papernot
LeArning Abstract Procedural Fairness Task Utility Pareto Frontier SGD Style Privacy Preserving Learning Fairness Mitigation

February 5, 2023

Improving Fair Training under Correlation Shifts
Yuji Roh, Kangwook Lee, Steven Euijong Whang, Changho Suh
Group Fairness Model Fairness Fair Algorithm Fairness Mitigation Correlation Shift Fair Training

November 11, 2022

Identifying, measuring, and mitigating individual unfairness for supervised learning models and application to credit risk models
Rasoul Shahsavarifar, Jithu Chandran, Mario Inchiosa, Amit Deshpande, Mario Schlener, Vishal Gossain, Yara Elias, Vinaya Murali
Application Proficiency Supervised Learning Group Fairness Individual Fairness Fairness Property Fairness Mitigation Credit Risk Model

October 30, 2022

Mitigating Unfairness via Evolutionary Multi-objective Ensemble Learning
Zhang Qingquan, Liu Jialin, Zhang Zeqi, Wen Junyi, Mao Bifei, Yao Xin
Fairness Metric Fairness Measure Fairness Mitigation Multiple Fairness Metric

September 20, 2022

Fairness and robustness in anti-causal prediction
Maggie Makar, Alexander D'Amour
Native Robustness Procedural Fairness Causal Structure Causal Prediction Fairness Criterion Fairness Mitigation

July 22, 2022

Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities
Pranav Dheram, Murugesan Ramakrishnan, Anirudh Raju, I-Fan Chen, Brian King, Katherine Powell, Melissa Saboowala, Karan Shetty, Andreas Stolcke
Speech Recognition Scientific Discovery Faulty Negative Mitigation Fairness Mitigation Expert Delineated Cohort Performance Disparity

March 23, 2022

Socially Fair Mitigation of Misinformation on Social Networks via Constraint Stochastic Optimization
Ahmed Abouzeid, Ole-Christoffer Granmo, Christian Webersik, Morten Goodwin
Social Network Misinformation Claim Misinformation Mitigation Fairness Mitigation Constrained Stochastic Optimization

March 9, 2022

Downstream Fairness Caveats with Synthetic Healthcare Data
Karan Bhanot, Ioana Baldini, Dennis Wei, Jiaming Zeng, Kristin P. Bennett
Synthetic Data Healthcare Data Healthcare Datasets Synthetic Medical Data Fairness Mitigation

November 11, 2021

FairAutoML: Embracing Unfairness Mitigation in AutoML
Qingyun Wu, Chi Wang
Online autoML Fair Machine Learning AutoML System Fairness Mitigation

November 4, 2021

Modeling Techniques for Machine Learning Fairness: A Survey
Mingyang Wan, Daochen Zha, Ninghao Liu, Na Zou
Timely Survey Procedural Fairness Fairness Metric Fair Model Fairness Issue Machine Learning Fairness Fairness Mitigation