PerFED-GAN: Personalized Federated Learning via Generative Adversarial Networks

Document Type


Publication Title

IEEE Internet of Things Journal


Federated learning is gaining popularity as a distributed machine learning method that can be used to deploy AI-dependent IoT applications while protecting client data privacy and security. Due to the differences of clients, a single global model may not perform well on all clients, so the personalized federated learning method, which trains a personalized model for each client that better suits its individual needs, becomes a research hotspot. Most personalized federated learning research, however, focuses on data heterogeneity while ignoring the need for model architecture heterogeneity. Most existing federated learning methods uniformly set the model architecture of all clients participating in federated learning, which is inconvenient for each client’s individual model and local data distribution requirements, and also increases the risk of client model leakage. This paper proposes a federated learning method based on co-training and generative adversarial networks(GANs) that allows each client to design its own model to participate in federated learning training independently without sharing any model architecture or parameter information with other clients or a center. In our experiments, the proposed method outperforms the existing methods in mean test accuracy by 42% when the client’s model architecture and data distribution vary significantly. Copyright © 2022, The Authors. All rights reserved.

First Page


Last Page




Publication Date



Data models, Collaborative work, Training, Computer architecture, Task analysis, Machine learning, Computational modeling, federated learning, personalized model, Non-IID data, co-training, generative adversarial networks


IR Deposit conditions:

OA version (pathway a): Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged