Fairness across different demographic groups is an essential criterion for face-related tasks, Face Attribute Classification (FAC) being a prominent example. Apart from this trend, Federated Learning (FL) is increasingly gaining traction as a scalable paradigm for distributed training. Existing FL approaches require data homogeneity to ensure fairness. However, this assumption is too restrictive in real-world settings. We propose F3, a novel FL framework for fair FAC under data heterogeneity. F3 adopts multiple heuristics to improve fairness across different demographic groups without requiring data homogeneity assumption. We demonstrate the efficacy of F3 by reporting empirically observed fairness measures and accuracy guarantees on popular face datasets. Our results suggest that F3 strikes a practical balance between accuracy and fairness for FAC.
@article{arxiv.2109.02351,
title = {F3: Fair and Federated Face Attribute Classification with Heterogeneous Data},
author = {Samhita Kanaparthy and Manisha Padala and Sankarshan Damle and Ravi Kiran Sarvadevabhatla and Sujit Gujar},
journal= {arXiv preprint arXiv:2109.02351},
year = {2022}
}
Comments
This paper is accepted as 2-page extended abstract at CODS-COMAD 2022 with title "Fair Federated Learning for Heterogeneous Face Data"