ProtoFL: Unsupervised Federated Learning via Prototypical Distillation
This work addresses scalability and privacy issues in federated learning for authentication, introducing a novel approach to improve one-class classification performance, though it is incremental as it builds on existing FL methods.
The paper tackles the challenges of limited communication and representation in federated learning for authentication systems by proposing ProtoFL, which uses prototypical representation distillation and a local one-class classifier to enhance the global model and reduce communication costs, achieving superior performance on benchmarks like MNIST, CIFAR-10, CIFAR-100, ImageNet-30, and Keystroke-Dynamics.
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.