Federated Fairness Analytics: Quantifying Fairness in Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dilley, Oscar, Parra-Ullauri, Juan Marcelo, Hussain, Rasheed, Simeonidou, Dimitra
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913468721922048
author Dilley, Oscar
Parra-Ullauri, Juan Marcelo
Hussain, Rasheed
Simeonidou, Dimitra
author_facet Dilley, Oscar
Parra-Ullauri, Juan Marcelo
Hussain, Rasheed
Simeonidou, Dimitra
contents Federated Learning (FL) is a privacy-enhancing technology for distributed ML. By training models locally and aggregating updates - a federation learns together, while bypassing centralised data collection. FL is increasingly popular in healthcare, finance and personal computing. However, it inherits fairness challenges from classical ML and introduces new ones, resulting from differences in data quality, client participation, communication constraints, aggregation methods and underlying hardware. Fairness remains an unresolved issue in FL and the community has identified an absence of succinct definitions and metrics to quantify fairness; to address this, we propose Federated Fairness Analytics - a methodology for measuring fairness. Our definition of fairness comprises four notions with novel, corresponding metrics. They are symptomatically defined and leverage techniques originating from XAI, cooperative game-theory and networking engineering. We tested a range of experimental settings, varying the FL approach, ML task and data settings. The results show that statistical heterogeneity and client participation affect fairness and fairness conscious approaches such as Ditto and q-FedAvg marginally improve fairness-performance trade-offs. Using our techniques, FL practitioners can uncover previously unobtainable insights into their system's fairness, at differing levels of granularity in order to address fairness challenges in FL. We have open-sourced our work at: https://github.com/oscardilley/federated-fairness.
format Preprint
id arxiv_https___arxiv_org_abs_2408_08214
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Federated Fairness Analytics: Quantifying Fairness in Federated Learning
Dilley, Oscar
Parra-Ullauri, Juan Marcelo
Hussain, Rasheed
Simeonidou, Dimitra
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Computer Science and Game Theory
Neural and Evolutionary Computing
Federated Learning (FL) is a privacy-enhancing technology for distributed ML. By training models locally and aggregating updates - a federation learns together, while bypassing centralised data collection. FL is increasingly popular in healthcare, finance and personal computing. However, it inherits fairness challenges from classical ML and introduces new ones, resulting from differences in data quality, client participation, communication constraints, aggregation methods and underlying hardware. Fairness remains an unresolved issue in FL and the community has identified an absence of succinct definitions and metrics to quantify fairness; to address this, we propose Federated Fairness Analytics - a methodology for measuring fairness. Our definition of fairness comprises four notions with novel, corresponding metrics. They are symptomatically defined and leverage techniques originating from XAI, cooperative game-theory and networking engineering. We tested a range of experimental settings, varying the FL approach, ML task and data settings. The results show that statistical heterogeneity and client participation affect fairness and fairness conscious approaches such as Ditto and q-FedAvg marginally improve fairness-performance trade-offs. Using our techniques, FL practitioners can uncover previously unobtainable insights into their system's fairness, at differing levels of granularity in order to address fairness challenges in FL. We have open-sourced our work at: https://github.com/oscardilley/federated-fairness.
title Federated Fairness Analytics: Quantifying Fairness in Federated Learning
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Computer Science and Game Theory
Neural and Evolutionary Computing
url https://arxiv.org/abs/2408.08214