Data Quality-Aware Client Selection in Heterogeneous Federated Learning

Shinan Song, Yaxin Li, Jin Wan, Xianghua Fu and Jingyan Jiang ()
Additional contact information
Shinan Song: School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China
Yaxin Li: School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China
Jin Wan: School of Electronic Information, Sichuan University, Chengdu 610017, China
Xianghua Fu: College of Bigdata and Internet, Shenzhen Technology University, Shenzhen 518118, China
Jingyan Jiang: College of Bigdata and Internet, Shenzhen Technology University, Shenzhen 518118, China

Mathematics, 2024, vol. 12, issue 20, 1-17

Abstract: Federated Learning (FL) enables decentralized data utilization while maintaining edge user privacy, but it faces challenges due to statistical heterogeneity. Existing approaches address client drift and data heterogeneity issues. However, real-world settings often involve low-quality data with noisy features, such as covariate drift or adversarial samples, which are usually ignored. Noisy samples significantly impact the global model’s accuracy and convergence rate. Assessing data quality and selectively aggregating updates from high-quality clients is crucial, but dynamically perceiving data quality without additional computations or data exchanges is challenging. In this paper, we introduce the FedDQA (Federated learning via Data Quality-Aware) (FedDQA) framework. We discover increased data noise leads to slower loss reduction during local model training. We propose a loss sharpness-based Data-Quality-Awareness (DQA) metric to differentiate between high-quality and low-quality data. Based on the DQA, we design a client selection algorithm that strategically selects participant clients to reduce the negative impact of noisy clients. Experiment results indicate that FedDQA significantly outperforms the baselines. Notably, it achieves up to a 4% increase in global model accuracy and demonstrates faster convergence rates.

Keywords: heterogeneous federated learning; data quality; loss sharpness; noisy data space (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/20/3229/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/20/3229/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:20:p:3229-:d:1499439

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().