Mitigating Group Bias in Federated Learning for Heterogeneous Devices
Open Access
- 3 June 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1043-1054
Abstract
Federated learning is emerging as a privacy-preserving model training approach in distributed edge applications. As such, most edge deployments are heterogeneous in nature, i.e., their sensing capabilities and environments vary across deployments. This edge heterogeneity violates the independence and identical distribution (IID) property of local data across clients. It produces biased global models, i.e., models that contribute to unfair decision-making and discrimination against a particular community or a group. Existing bias mitigation techniques only focus on bias generated from label heterogeneity in non-IID data without accounting for domain variations due to feature heterogeneity. Our work proposes a group-fair FL framework that minimizes group-bias while preserving privacy. Our main idea is to leverage average conditional probabilities to compute a cross-domain group importance weights derived from heterogeneous training data to optimize the performance of the worst-performing group using a modified multiplicative weights update method. Additionally, we propose regularization techniques to minimize the difference between the worst and best-performing groups while ensuring through our thresholding mechanism to strike a balance between bias reduction and group performance degradation. Our evaluation of image classification benchmarks assesses the fair decision-making of our framework in real-world settings.Keywords
All Related Versions
This publication has 41 references indexed in Scilit:
- Privacy-Preserving federated learning in medical diagnosis with homomorphic re-EncryptionComputer Standards & Interfaces, 2022
- Federated learning for COVID-19 screening from Chest X-ray imagesApplied Soft Computing, 2021
- Collaborative Fairness in Federated Learning2020
- Fairness-Aware Classifier with Prejudice Remover Regularizer2012
- Large-Scale Machine Learning with Stochastic Gradient Descent2010
- Adapting Visual Category Models to New Domains2010
- Multi-objective tabu search using a multinomial probability mass functionEuropean Journal of Operational Research, 2006
- Developing multimodal intelligent affective interfaces for tele-home health careInternational Journal of Human-Computer Studies, 2003
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A database for handwritten text recognition researchIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994