Overhead-free Noise-tolerant Federated Learning: A New Baseline

doi:10.1007/s11633-023-1449-1

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Overhead-free Noise-tolerant Federated Learning: A New Baseline
	Shiyi Lin 1; Deming Zhai 1; Feilong Zhang 1; Junjun Jiang 1; Xianming Liu 1; Xiangyang Ji 2
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:3 页码:526-537
摘要	Federated learning (FL) is a promising decentralized machine learning approach that enables multiple distributed clients to train a model jointly while keeping their data private. However, in real-world scenarios, the supervised training data stored in local clients inevitably suffer from imperfect annotations, resulting in subjective, inconsistent and biased labels. These noisy labels can harm the collaborative aggregation process of FL by inducing inconsistent decision boundaries. Unfortunately, few attempts have been made towards noise-tolerant federated learning, with most of them relying on the strategy of transmitting overhead messages to assist noisy labels detection and correction, which increases the communication burden as well as privacy risks. In this paper, we propose a simple yet effective method for noise-tolerant FL based on the well-established co-training framework. Our method leverages the inherent discrepancy in the learning ability of the local and global models in FL, which can be regarded as two complementary views. By iteratively exchanging samples with their high confident predictions, the two models “teach each other” to suppress the influence of noisy labels. The proposed scheme enjoys the benefit of overhead cost-free and can serve as a robust and efficient baseline for noise-tolerant federated learning. Experimental results demonstrate that our method outperforms existing approaches, highlighting the superiority of our method.
关键词	Federated learning, noise-label learning, privacy-preserving machine learning, edge intelligence, distributed machine learning
DOI	10.1007/s11633-023-1449-1
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56480
专题	学术期刊_Machine Intelligence Research
作者单位	1.Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150000, China 2.Department of Automation, Tsinghua University, Beijing 100084, China
推荐引用方式 GB/T 7714	Shiyi Lin,Deming Zhai,Feilong Zhang,et al. Overhead-free Noise-tolerant Federated Learning: A New Baseline[J]. Machine Intelligence Research,2024,21(3):526-537.
APA	Shiyi Lin,Deming Zhai,Feilong Zhang,Junjun Jiang,Xianming Liu,&Xiangyang Ji.(2024).Overhead-free Noise-tolerant Federated Learning: A New Baseline.Machine Intelligence Research,21(3),526-537.
MLA	Shiyi Lin,et al."Overhead-free Noise-tolerant Federated Learning: A New Baseline".Machine Intelligence Research 21.3(2024):526-537.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2023-03-027.pdf（1816KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载