Personalized Privacy-Preserving Framework for Cross-Silo Federated Learning

TL;DR

This paper introduces PPPFL, a novel federated learning framework that enhances privacy and personalization by combining differential privacy, generative models, and meta-learning to address data privacy and non-IID challenges.

Contribution

The paper proposes a personalized, privacy-preserving federated learning framework using synthetic data generation and meta-learning, improving performance and privacy in cross-silo FL.

Findings

Outperforms baseline FL methods on multiple datasets

Effectively protects client data privacy

Improves model personalization and robustness

Abstract

Federated learning (FL) is recently surging as a promising decentralized deep learning (DL) framework that enables DL-based approaches trained collaboratively across clients without sharing private data. However, in the context of the central party being active and dishonest, the data of individual clients might be perfectly reconstructed, leading to the high possibility of sensitive information being leaked. Moreover, FL also suffers from the nonindependent and identically distributed (non-IID) data among clients, resulting in the degradation in the inference performance on local clients' data. In this paper, we propose a novel framework, namely Personalized Privacy-Preserving Federated Learning (PPPFL), with a concentration on cross-silo FL to overcome these challenges. Specifically, we introduce a stabilized variant of the Model-Agnostic Meta-Learning (MAML) algorithm to collaboratively train a global initialization from clients' synthetic data generated by Differential Private Generative Adversarial Networks (DP-GANs). After reaching convergence, the global initialization will be locally adapted by the clients to their private data. Through extensive experiments, we empirically show that our proposed framework outperforms multiple FL baselines on different datasets, including MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100.