AdaFedFR: Federated Face Recognition with Adaptive Inter-Class Representation Learning

TL;DR

AdaFedFR is a federated face recognition framework that improves model generalization and training efficiency using adaptive inter-class representation learning, achieving high performance with minimal communication rounds.

Contribution

The paper introduces AdaFedFR, a novel federated learning approach that leverages public identity features as negative knowledge for enhanced privacy-preserving face recognition.

Findings

Outperforms previous methods on face recognition benchmarks

Achieves high accuracy within less than 3 communication rounds

Enhances model generalization and training efficiency

Abstract

With the growing attention on data privacy and communication security in face recognition applications, federated learning has been introduced to learn a face recognition model with decentralized datasets in a privacy-preserving manner. However, existing works still face challenges such as unsatisfying performance and additional communication costs, limiting their applicability in real-world scenarios. In this paper, we propose a simple yet effective federated face recognition framework called AdaFedFR, by devising an adaptive inter-class representation learning algorithm to enhance the generalization of the generic face model and the efficiency of federated training under strict privacy-preservation. In particular, our work delicately utilizes feature representations of public identities as learnable negative knowledge to optimize the local objective within the feature space, which further encourages the local model to learn powerful representations and optimize personalized models for clients. Experimental results demonstrate that our method outperforms previous approaches on several prevalent face recognition benchmarks within less than 3 communication rounds, which shows communication-friendly and great efficiency.