paper-with-me

홈 › Papers

Federated Learning with GAN-based Data Synthesis for Non-IID Clients

2022-06-11 · Zijian Li, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang

Federated learning (FL) has recently emerged as a popular privacy-preserving collaborative learning paradigm. However, it suffers from the non-independent and identically distributed (non-IID) data among clients. In this paper, we propose a novel framework, named Synthetic Data Aided Federated Learning (SDA-FL), to resolve this non-IID challenge by sharing synthetic data. Specifically, each client pretrains a local generative adversarial network (GAN) to generate differentially private synthetic data, which are uploaded to the parameter server (PS) to construct a global shared synthetic dataset. To generate confident pseudo labels for the synthetic dataset, we also propose an iterative pseudo labeling mechanism performed by the PS. A combination of the local private dataset and synthetic dataset with confident pseudo labels leads to nearly identical data distributions among clients, which improves the consistency among local models and benefits the global aggregation. Extensive experiments evidence that the proposed framework outperforms the baseline methods by a large margin in several benchmark datasets under both the supervised and semi-supervised settings.

📄 PDF Abstract BibTeX arXiv:2206.05507

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningGenerative Adversarial NetworkPrivacy Preserving

Similar Papers 제목 키워드 기반

Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning

2025-01-04 · Zhongwei Wang, Tong Wu, Zhiyong Chen, Liang Qian 외

Federated semi-supervised learning (FSSL) is primarily challenged by two factors: the scarcity of labeled data across clients and the non-independent and identically distribution (non-IID) nature of data among clients. I…

Federated Learning

Federated Neural Compression Under Heterogeneous Data

2023-05-25 · Eric Lei, Hamed Hassani, Shirin Saeedi Bidokhti

We discuss a federated learned compression problem, where the goal is to learn a compressor from real-world data which is scattered across clients and may be statistically heterogeneous, yet share a common underlying rep…

Federated LearningPersonalized Federated Learning

Bias-Free FedGAN: A Federated Approach to Generate Bias-Free Datasets

2021-03-17 · Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal, Shlomo Dubnov

Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive training data. In this paper, we experimen…

Generative Adversarial NetworkImage Generation

What Do We Mean by Generalization in Federated Learning?

2021-10-27 · ICLR 2022 4 · Honglin Yuan, Warren Morningstar, Lin Ning, Karan Singhal

Federated learning data is drawn from a distribution of distributions: clients are drawn from a meta-distribution, and their data are drawn from local data distributions. Thus generalization studies in federated learning…

Federated Learning

IMFL-AIGC: Incentive Mechanism Design for Federated Learning Empowered by Artificial Intelligence Generated Content

2024-06-12 · Guangjing Huang, Qiong Wu, Jingyi Li, Xu Chen

Federated learning (FL) has emerged as a promising paradigm that enables clients to collaboratively train a shared global model without uploading their local data. To alleviate the heterogeneous data quality among client…

Federated Learning