Federated Fairness Analytics: Quantifying Fairness in Federated Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |