Local Fairness

Local fairness in machine learning aims to ensure that algorithms treat individuals equitably not just globally, but also within specific subgroups or local neighborhoods defined by features or proximity in data space. Current research focuses on developing methods that balance global and local fairness, often employing techniques like adversarial debiasing, constrained optimization, and information-theoretic approaches within federated learning and graph-based models. This work is crucial for mitigating algorithmic bias and promoting fairness in various applications, addressing concerns about disparities that may persist even when global fairness metrics are satisfied. The ultimate goal is to create more equitable and trustworthy AI systems.

Papers

February 2, 2024

Federated Unlearning: a Perspective of Stability and Fairness
Jiaqi Shao, Tao Lin, Xuanyu Cao, Bing Luo
Procedural Fairness Core Stability Visual Perspective Data Heterogeneity Unlearning Framework Harmful Unlearning Federated Unlearning Local Fairness

January 26, 2024

Keeping the Harmony Between Neighbors: Local Fairness in Graph Fair Division
Halvard Hummel, Ayumi Igarashi
Thy Neighbor Structured Graph Local Fairness Indivisible Good

January 7, 2024

GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning
Syed Irfan Ali Meerza, Luyang Liu, Jiaxin Zhang, Jian Liu
World Event Model Fairness Fairness Notion Local Fairness

November 20, 2023

Certification of Distributional Individual Fairness
Matthew Wicker, Vihari Piratia, Adrian Weller
Algorithmic Fairness Individual Fairness Local Fairness Quasi Convex Optimization

October 27, 2023

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
Vincent Grari, Thibault Laugel, Tatsunori Hashimoto, Sylvain Lamprier, Marcin Detyniecki
Robust Optimization Algorithmic Fairness Fairness Notion Adversarial Debiasing Fair Adversarial Fairness Learning Local Fairness

July 21, 2023

Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
Faisal Hamman, Sanghamitra Dutta
Group Fairness Information Theoretic Local Explanation Information Decomposition Fairness Performance Trade Local Fairness

May 17, 2023

Mitigating Group Bias in Federated Learning: Beyond Local Fairness
Ganghua Wang, Ali Payani, Myungjin Lee, Ramana Kompella
Group Fairness Model Fairness Mitigating Bias Local Fairness Fairness Aware Training Fair Training

December 22, 2022

Graph Learning with Localized Neighborhood Fairness
April Chen, Ryan Rossi, Nedim Lipka, Jane Hoffswell, Gromit Chan, Shunan Guo, Eunyee Koh, Sungchul Kim, Nesreen K. Ahmed
Link Prediction Graph Learning Fair Graph Local Fairness

May 5, 2022

On Disentangled and Locally Fair Representations
Yaron Gurovich, Sagie Benaim, Lior Wolf
Fair Representation Disentangled Haze Local Fairness