Fairness Accuracy

Fairness-accuracy trade-offs in machine learning explore the inherent tension between building accurate predictive models and ensuring those models don't unfairly discriminate against specific demographic groups. Current research focuses on developing algorithms and model architectures (including neural networks and graph neural networks) that mitigate bias through various techniques like sample weighting, personalized federated learning, and post-processing methods, aiming to optimize the balance between these competing objectives. This field is crucial for ensuring responsible AI deployment across diverse applications, impacting areas like criminal justice, healthcare, and finance by promoting equitable and trustworthy algorithmic decision-making. A significant focus is on developing robust methods for evaluating and comparing fairness-accuracy trade-offs across different datasets and fairness metrics.

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 21, 2024

Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium
Mehdi Yazdani-Jahromi, Ali Khodabandeh Yalabadi, AmirArsalan Rajabi, Aida Tayebi, Ivan Garibay, Ozlem Ozmen Garibay
Neural Network Bilevel Optimization Fairness Accuracy Fairness Aware Machine Achieving Fairness Fairness Objective Stackelberg Equilibrium Fairness Method

October 2, 2024

Fair Class-Incremental Learning using Sample Weighting
Jaeyoung Park, Minsu Kim, Steven Euijong Whang
Class Incremental Learning Model Fairness Fairness Accuracy Sample Weight Fairness Aware Learning

September 25, 2024

ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods
MaryBeth Defrance, Maarten Buyl, Tijl De Bie
Bias Mitigation Binary Classification Fairness Notion Fairness Accuracy Fairness Benchmark

July 27, 2024

Enhancing Group Fairness in Federated Learning through Personalization
Yifan Yang, Ali Payani, Parinaz Naghizadeh
Personalized Federated Learning Group Fairness Fairness Accuracy Fair Clustering

July 16, 2024

Fairly Accurate: Optimizing Accuracy Parity in Fair Target-Group Detection
Soumyajit Gupta, Venelin Kovatchev, Maria De-Arteaga, Matthew Lease
Loss Function Toxicity Detection Fairness Accuracy Fair Classification Fairness Objective Accuracy Disparity

May 24, 2024

Fairness-Accuracy Trade-Offs: A Causal Perspective
Drago Plecko, Elias Bareinboim
Fairness Constraint Fairness Accuracy Causal Fairness

May 12, 2024

Intrinsic Fairness-Accuracy Tradeoffs under Equalized Odds
Meiyu Zhong, Ravi Tandon
Machine Learning Procedural Fairness Fairness Accuracy FAir Classifier Equalized Odds

April 28, 2024

Enhancing Fairness in Neural Networks Using FairVIC
Charmaine Barker, Daniel Bethell, Dimitar Kazakov
Neural Network Deep Learning Model Procedural Fairness Fairness Accuracy

March 27, 2024

Minimax Optimal Fair Classification with Bounded Demographic Disparity
Xianli Zeng, Guang Cheng, Edgar Dobriban
Fairness Constraint Fairness Accuracy Fairness Aware Optimal Fair

February 27, 2024

Achievable Fairness on Your Data With Utility Guarantees
Muhammad Faaiz Taufiq, Jean-Francois Ton, Yang Liu
Raw Data Model Fairness Fairness Accuracy Fairness Method Fairness Performance Machine Learning Fairness High Probability Guarantee

February 20, 2024

Fairness Without Harm: An Influence-Guided Active Sampling Approach
Jinlong Pang, Jialu Wang, Zhaowei Zhu, Yuanshun Yao, Chen Qian, Yang Liu
Procedural Fairness Group Fairness Potential Harm Fairness Accuracy Pareto Frontier Active Sampling

February 14, 2024

Inference for an Algorithmic Fairness-Accuracy Frontier
Yiqi Liu, Francesca Molinari
Scientific Inference Fairness Accuracy Consistent Estimator Policy Recommendation

January 29, 2024

FedFair^3: Unlocking Threefold Fairness in Federated Learning
Simin Javaherian, Sanjeev Panta, Shelby Williams, Md Sirajul Islam, Li Chen
Fairness Accuracy Rethinking Fairness

December 16, 2023

How Far Can Fairness Constraints Help Recover From Biased Data?
Mohit Sharma, Amit Deshpande
Fairness Constraint Prompt Recovery Fairness Accuracy Fair Classification FAir Classifier Biased Data

December 6, 2023

f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization
Sina Baharlouei, Shivam Patel, Meisam Razaviyayn
Empirical Risk Minimization Stochastic Optimization Fairness Accuracy

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

November 21, 2023

Fair Text Classification with Wasserstein Independence
Thibaud Leteno, Antoine Gourru, Charlotte Laclau, Rémi Emonet, Christophe Gravier
Adversarial Training Text Classification Group Fairness Fairness Accuracy Fair Classification Wasserstein Dictionary Neural Text Classification

October 19, 2023

A Theoretical Approach to Characterize the Accuracy-Fairness Trade-off Pareto Frontier
Hua Tang, Lu Cheng, Ninghao Liu, Mengnan Du
Fair Machine Learning Fairness Accuracy

October 11, 2023

Fairness under Covariate Shift: Improving Fairness-Accuracy tradeoff with few Unlabeled Test Samples
Shreyas Havaldar, Jatin Chauhan, Karthikeyan Shanmugam, Jay Nandy, Aravindan Raghuveer
Procedural Fairness Covariate Shift Fairness Accuracy Unlabeled Sample Test Loss