Meta-Learning for Federated Face Recognition in Imbalanced Data Regimes

TL;DR

This paper introduces a meta-learning approach called HF-MAML for federated face recognition, improving verification accuracy and fairness in heterogeneous data environments while preserving user privacy.

Contribution

It proposes HF-MAML for federated face recognition, addressing data heterogeneity and enhancing global model performance and fairness.

Findings

HF-MAML outperforms existing models on CelebA partitions.

Embedding regularization improves global verification scores.

HF-MAML enhances fairness by reducing score variability.

Abstract

The growing privacy concerns surrounding face image data demand new techniques that can guarantee user privacy. One such face recognition technique that claims to achieve better user privacy is Federated Face Recognition (FRR), a subfield of Federated Learning (FL). However, FFR faces challenges due to the heterogeneity of the data, given the large number of classes that need to be handled. To overcome this problem, solutions are sought in the field of personalized FL. This work introduces three new data partitions based on the CelebA dataset, each with a different form of data heterogeneity. It also proposes Hessian-Free Model Agnostic Meta-Learning (HF-MAML) in an FFR setting. We show that HF-MAML scores higher in verification tests than current FFR models on three different CelebA data partitions. In particular, the verification scores improve the most in heterogeneous data partitions. To balance personalization with the development of an effective global model, an embedding regularization term is introduced for the loss function. This term can be combined with HF-MAML and is shown to increase global model verification performance. Lastly, this work performs a fairness analysis, showing that HF-MAML and its embedding regularization extension can improve fairness by reducing the standard deviation over the client evaluation scores.