Fairness Intervention

Fairness intervention in machine learning aims to mitigate algorithmic bias and ensure equitable outcomes across different demographic groups. Current research focuses on developing and evaluating fairness-enhancing techniques across various stages of the machine learning pipeline, including pre-processing, in-processing, and post-processing methods, often employing causal inference and constrained optimization approaches. These efforts are crucial for building trustworthy and responsible AI systems, addressing concerns about discrimination in high-stakes applications like loan applications, hiring, and education, and promoting fairness in areas such as flood adaptation and sequential recommendation. The field is actively exploring the interplay between fairness, accuracy, and uncertainty, as well as the cumulative effects of multiple interventions.

Papers

October 2, 2024

FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness
Lucas Rosenblatt, R. Teal Witter
High Uncertainty Anticipation Algorithmic Fairness Predictive Uncertainty Comprehensive Benchmark Fair Predictor Fairness Intervention Calibrated Uncertainty

September 29, 2024

Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems
Xuyang Wu, Shuowei Li, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang
Language Model Medical LLM Retrieval Augmented Generation Procedural Fairness Open Ended Fairness Evaluation Fairness Intervention

July 26, 2024

FairAIED: Navigating Fairness, Bias, and Ethics in Educational AI Applications
Sribala Vidyadhari Chinta, Zichong Wang, Zhipeng Yin, Nhat Hoang, Matthew Gonzalez, Tai Le Quy, Wenbin Zhang
Absolute Stance Bias Algorithmic Fairness Intercultural Ethic Fairness Intervention

June 24, 2024

Addressing Polarization and Unfairness in Performative Prediction
Kun Jin, Tian Xie, Yang Liu, Xueru Zhang
Political Polarization Performative Prediction Fairness Intervention Fairness Method Group Loss Data Distribution Shift

April 18, 2024

The Neutrality Fallacy: When Algorithmic Fairness Interventions are (Not) Positive Action
Hilde Weerts, Raphaële Xenidis, Fabien Tarissan, Henrik Palmer Olsen, Mykola Pechenizkiy
Fairness Intervention

January 19, 2024

Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach
Aoqi Zuo, Yiqing Li, Susan Wei, Mingming Gong
Causal Inference Causal Graph Constrained Optimization Fairness Intervention Causal Fairness Causal DAG Fair Prediction

December 6, 2023

Exposing Disparities in Flood Adaptation for Equitable Future Interventions
Lidia Cano Pecharroman, ChangHoon Hahn
Health Disparity Fairness Intervention Climate Change Adaptation Flood Adaptation

July 27, 2023

Fair Machine Unlearning: Data Removal while Mitigating Disparities
Alex Oesterling, Jiaqi Ma, Flavio P. Calmon, Hima Lakkaraju
Machine Learning Model Machine Unlearning Unlearning Framework Unlearning Method Fairness Intervention Fairness Performance Data Removal Mitigating Disparity

June 15, 2023

Arbitrariness Lies Beyond the Fairness-Accuracy Frontier
Carol Xuan Long, Hsiang Hsu, Wael Alghamdi, Flavio P. Calmon
Group Fairness Fairness Accuracy Fairness Intervention Predictive Multiplicity Algorithmic Arbitrariness

June 12, 2023

Towards Fair and Explainable AI using a Human-Centered AI Approach
Bhavya Ghai
Machine Learning Explainable AI High Explainability Fairness Intervention Human Centered Evaluation

May 30, 2023

Adapting Fairness Interventions to Missing Values
Raymond Feng, Flavio P. Calmon, Hao Wang
Group Fairness Algorithmic Fairness Policy Value Fair Classification Fairness Intervention

February 3, 2023

An Operational Perspective to Fairness Interventions: Where and How to Intervene
Brian Hsu, Xiaotong Chen, Ying Han, Hongseok Namkoong, Kinjal Basu
Inductive Bias Fairness Intervention Early Intervention Operational Technology

January 27, 2023

Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions
Hao Wang, Luxi He, Rui Gao, Flavio P. Calmon
Machine Learning Fairness Constraint Fundamental Limit Fairness Intervention Epistemic State Non Gaussian Aleatoric Uncertainty

December 5, 2022

Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling
Junhyun Nam, Sangwoo Mo, Jaeho Lee, Jinwoo Shin
Negative Sampling Spurious Correlation Conditional Generative Label Distribution Conditional Generation Spurious Feature Fairness Intervention

June 23, 2022

Context matters for fairness -- a case study on the effect of spatial distribution shifts
Siamak Ghodsi, Harith Alani, Eirini Ntoutsi
Case Study Procedural Fairness Mixed Effect Context Information Distribution Shift Temporal Shift Fairness Intervention Balancing Fairness Fairness Aware Learning

June 1, 2022

How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis
Bishwamittra Ghosh, Debabrota Basu, Kuldeep S. Meel
Feature Wise Fairness Intervention Biased Classifier Global Sensitivity Analysis Group Fairness Metric Fairness Influence Function

May 6, 2022

Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches
Lindsay Weinberg
AI Fairness Interdisciplinary Perspective Fairness Intervention Lower Critique Accuracy ML Fairness Rethinking Fairness

May 1, 2022

Domain Adaptation meets Individual Fairness. And they get along
Debarghya Mukherjee, Felix Petersen, Mikhail Yurochkin, Yuekai Sun
Domain Adaptation Distribution Shift Algorithmic Fairness Algorithmic Bias Individual Fairness Fairness Intervention

April 30, 2022

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
Cheng-Te Li, Cheng Hsu, Yang Zhang
Multi Task Learning Sequential Recommendation Fairness Intervention Preference Representation Recommendation Fairness Fairness Aware Graph Fairness Aware Recommendation

April 21, 2022

A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms
Nil-Jana Akpinar, Manish Nagireddy, Logan Stapleton, Hao-Fei Cheng, Haiyi Zhu, Steven Wu, Hoda Heidari
Bias Evaluation Fairness Intervention Fairness Implication FAIrness Testing Sandbox Environment

Fairness Intervention

Papers

FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness

Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems

FairAIED: Navigating Fairness, Bias, and Ethics in Educational AI Applications

Addressing Polarization and Unfairness in Performative Prediction

The Neutrality Fallacy: When Algorithmic Fairness Interventions are (Not) Positive Action

Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach

Exposing Disparities in Flood Adaptation for Equitable Future Interventions

Fair Machine Unlearning: Data Removal while Mitigating Disparities

Arbitrariness Lies Beyond the Fairness-Accuracy Frontier

Towards Fair and Explainable AI using a Human-Centered AI Approach

Adapting Fairness Interventions to Missing Values

An Operational Perspective to Fairness Interventions: Where and How to Intervene

Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions

Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling

Context matters for fairness -- a case study on the effect of spatial distribution shifts

How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysis

Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches

Domain Adaptation meets Individual Fairness. And they get along

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms