Fair Learning

Fair learning aims to mitigate biases in machine learning models that disproportionately affect certain demographic groups, ensuring equitable outcomes across different populations. Current research focuses on developing algorithms and techniques to address various forms of bias, including those stemming from imbalanced datasets, unidentified biases in high-dimensional data, and strategic manipulation by users, often employing methods like self-training, regularization, and distributionally robust optimization. This field is crucial for building trustworthy and ethical AI systems, impacting diverse applications from healthcare and criminal justice to hiring and loan applications by promoting fairness and accountability in algorithmic decision-making.

Papers

November 12, 2024

A Stochastic Optimization Framework for Private and Fair Learning From Decentralized Data
Devansh Gupta, A.S. Poornash, Andrew Lowy, Meisam Razaviyayn
Differential Privacy Decentralized Data Fairness Notion Fairness Accuracy FAIR Federated Learning Fair Learning

October 23, 2024

Learning Fair and Preferable Allocations through Neural Network
Ryota Maruo, Koh Takeuchi, Hisashi Kashima
Neural Network Fairness Constraint Fairness Notion Fairness Criterion Fair Learning Fair Allocation Efficient Allocation

September 30, 2024

DCAST: Diverse Class-Aware Self-Training Mitigates Selection Bias for Fairer Learning
Yasin I. Tepeli, Joana P. Gonçalves
Inductive Bias Class Imbalance Self Training Model Bias Fair Learning

February 29, 2024

To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models
Cyrus Cousins, I. Elizabeth Kumar, Suresh Venkatasubramanian
Fair Machine Learning Fairness Aware Machine Regularization Effect Rademacher Complexity Tight Bound Fair Learning Shared Model Fair Training

February 28, 2024

On the Inductive Biases of Demographic Parity-based Fair Learning Algorithms
Haoyu Lei, Amin Gohari, Farzan Farnia
Inductive Bias Fair Machine Learning Sensitive Attribute FAir Classifier Fairness Aware Machine Socio Demographic Fair Learning

February 7, 2024

Learning Fair Ranking Policies via Differentiable Optimization of Ordered Weighted Averages
My H. Dinh, James Kotary, Ferdinando Fioretto
Learning to Rank Fair Learning Differentiable Optimization Weighted Average Fair Ranking Fair Learning to Rank

November 15, 2023

Learning Fair Division from Bandit Feedback
Hakuei Yamada, Junpei Komiyama, Kenshi Abe, Atsushi Iwasaki
Regret Bound Bandit Feedback Online Algorithm Welfare Maximization Fair Learning Fisher Market

October 17, 2023

Group-blind optimal transport to group parity and its constrained variants
Quan Zhou, Jakub Marecek
Procedural Fairness Optimal Transport Natural Language Oriented Variant Fair Learning Unbiased SGG Group Parity

October 8, 2023

FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Raman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy Hospedales
Procedural Fairness Parameter Efficient Fine Tuning Medical Image Analysis Generalization Gap Fairness Perception Fair Learning Fairness Learning

September 23, 2023

Penalties and Rewards for Fair Learning in Paired Kidney Exchange Programs
Margarida Carvalho, Alison Caulfield, Yi Lin, Adrian Vetta
Reward Report Fair Learning Appropriate Penalty Term Egalitarian Fairness

September 4, 2023

Classic algorithms are fair learners: Classification Analysis of natural weather and wildfire occurrences
Senthilkumar Gopal
Supervised Learning Decision Tree Sparse Data Extreme Event Classification Problem Classical Algorithm Fair Learning Forest Wildfire Observation

March 29, 2023

Fairlearn: Assessing and Improving Fairness of AI Systems
Hilde Weerts, Miroslav Dudík, Richard Edgar, Adrin Jalali, Roman Lutz, Michael Madaio
Artificial Intelligence Procedural Fairness Artificial Intelligence System Fairness Improvement Fair Learning Fairness Issue

February 11, 2023

Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP
Xudong Han, Timothy Baldwin, Trevor Cohn
Procedural Fairness NLP Field Model Selection Fairness Research Fair Learning Fairness Property

November 11, 2022

Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes
Tennison Liu, Alex J. Chan, Boris van Breugel, Mihaela van der Schaar
Algorithmic Fairness Fair Machine Learning Sensitive Attribute Practical Approach Fair Predictor Fair Learning

October 19, 2022

On Learning Fairness and Accuracy on Multiple Subgroups
Changjian Shui, Gezheng Xu, Qi Chen, Jiaqi Li, Charles Ling, Tal Arbel, Boyu Wang, Christian Gagné
Bilevel Optimization Fair Predictor Fair Learning Subgroup Description Fair Prediction Fairness Learning

October 17, 2022

Stochastic Differentially Private and Fair Learning
Andrew Lowy, Devansh Gupta, Meisam Razaviyayn
Differential Privacy Stochastic Way Fair Machine Learning Fairness Notion Private Algorithm Fair Learning

August 16, 2022

Error Parity Fairness: Testing for Group Fairness in Regression Tasks
Furkan Gursoy, Ioannis A. Kakadiaris
Group Fairness Level Test Regression Task Fairness Accuracy Fair Learning FAIrness Testing Fair Regression

June 9, 2022

Individually Fair Learning with One-Sided Feedback
Yahav Bechavod, Aaron Roth
Biased Feedback Fair Learning Contextual Combinatorial

May 30, 2022

Metrizing Fairness
Yves Rychener, Bahar Taskesen, Daniel Kuhn
Group Fairness Fairness Accuracy Fairness Aware Machine Fair Learning Statistical Fairness

May 26, 2022

Fair Representation Learning through Implicit Path Alignment
Changjian Shui, Qi Chen, Jiaqi Li, Boyu Wang, Christian Gagné
Bi Level Optimization Multiple Level Fair Representation Learning Fair Learning Invariant Predictor