FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Data
This addresses the problem of balancing generalization and personalization in federated learning for industrial applications with data privacy concerns, representing a novel method rather than an incremental improvement.
The paper tackled the challenge of handling non-IID data in federated learning by proposing FedBKD, a data-free distillation framework that uses GANs for synthetic data and bidirectional knowledge distillation, achieving state-of-the-art performances on 4 benchmarks under various non-IID settings.
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.