ProtoFL: Unsupervised Federated Learning via Prototypical Distillation

TL;DR

ProtoFL introduces an unsupervised federated learning framework that enhances global model representations and reduces communication rounds, utilizing prototypical distillation and a novel local one-class classifier, with strong experimental results.

Contribution

This work is the first to apply federated learning to improve one-class classification performance using prototypical representation distillation.

Findings

Outperforms previous methods on five benchmark datasets.

Reduces communication rounds in federated learning.

Improves one-class classification accuracy.

Abstract

Federated learning (FL) is a promising approach for enhancing data privacy preservation, particularly for authentication systems. However, limited round communications, scarce representation, and scalability pose significant challenges to its deployment, hindering its full potential. In this paper, we propose 'ProtoFL', Prototypical Representation Distillation based unsupervised Federated Learning to enhance the representation power of a global model and reduce round communication costs. Additionally, we introduce a local one-class classifier based on normalizing flows to improve performance with limited data. Our study represents the first investigation of using FL to improve one-class classification performance. We conduct extensive experiments on five widely used benchmarks, namely MNIST, CIFAR-10, CIFAR-100, ImageNet-30, and Keystroke-Dynamics, to demonstrate the superior performance of our proposed framework over previous methods in the literature.