FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Data

TL;DR

FedBKD introduces a data-free distillation framework using GANs for federated learning, enhancing both global generalization and local personalization on non-IID data without risking data leakage.

Contribution

The paper proposes a novel data-free knowledge distillation method with GANs for federated learning, balancing global and local model performance on non-IID data.

Findings

Achieves state-of-the-art results on 4 benchmarks.

Effectively handles non-IID data without public datasets.

Improves both global and local model performance.

Abstract

Federated learning (FL) is a decentralized collaborative machine learning (ML) technique. It provides a solution to the issues of isolated data islands and data privacy leakage in industrial ML practices. One major challenge in FL is handling the non-identical and independent distributed (non-IID) data. Current solutions either focus on constructing an all-powerful global model, or customizing personalized local models. Few of them can provide both a well-generalized global model and well-performed local models at the same time. Additionally, many FL solutions to the non-IID problem are benefited from introducing public datasets. However, this will also increase the risk of data leakage. To tackle the problems, we propose a novel data-free distillation framework, Federated Bidirectional Knowledge Distillation (FedBKD). Specifically, we train Generative Adversarial Networks (GAN) for synthetic data. During the GAN training, local models serve as discriminators and their parameters are frozen. The synthetic data is then used for bidirectional distillation between global and local models to achieve knowledge interactions so that performances for both sides are improved. We conduct extensive experiments on 4 benchmarks under different non-IID settings. The results show that FedBKD achieves SOTA performances in every case.