Community Fairness

Community fairness in machine learning focuses on ensuring algorithmic systems perform equitably across different groups and communities, addressing both group-level disparities (e.g., based on race or gender) and disparities in model accuracy across communities. Current research emphasizes developing methods, often involving post-processing techniques or linear programming, to simultaneously achieve both group and community fairness while maintaining model utility. This work is crucial for mitigating bias and promoting equitable outcomes in applications like healthcare, finance, and criminal justice, where algorithmic decisions impact diverse populations.

Papers

May 28, 2024

Post-Fair Federated Learning: Achieving Group and Community Fairness in Federated Learning via Post-processing
Yuying Duan, Yijun Tian, Nitesh Chawla, Michael Lemmon
Procedural Fairness Group Fairness Group Setting Fairness Notion Community Fairness

February 19, 2024

AI Fairness in Practice
David Leslie, Cami Rincon, Morgan Briggs, Antonella Perini, Smera Jayadeva, Ann Borda, SJ Bennett, Christopher Burr, Mhairi Aitken, Michael Katell, Claudia Fischer, Janis Wong, Ismael Kherroubi Garcia
Practice Mode AI Ethic AI Fairness FAIR Data Community Fairness

April 14, 2023

Systemic Fairness
Arindam Ray, Balaji Padmanabhan, Lina Bouayad
Algorithmic Fairness Fairness Issue Fairness Performance Community Fairness

Community Fairness

Papers

Post-Fair Federated Learning: Achieving Group and Community Fairness in Federated Learning via Post-processing

AI Fairness in Practice

Systemic Fairness