Data source selection in federated learning: A submodular optimization approach

• Main Authors: ZHANG, Ruisheng, WANG, Yansheng, ZHOU, Zimu, REN, Ziyao, TONG, Yongxin, XU, Ke
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Federated learning; Data source selection; Submodularity; Databases and Information Systems; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7219; https://ink.library.smu.edu.sg/context/sis_research/article/8222/viewcontent/dasfaa22_zhang.pdf
• Institution: Singapore Management University

Federated learning is a new learning paradigm that jointly trains a model from multiple data sources without sharing raw data. For the practical deployment of federated learning, data source selection is compulsory due to the limited communication cost and budget in real-world applications. The necessity of data source selection is further amplified in presence of data heterogeneity among clients. Prior solutions are either low in efficiency with exponential time cost or lack theoretical guarantees. Inspired by the diminishing marginal accuracy phenomenon in federated learning, we study the problem from the perspective of submodular optimization. In this paper, we aim at efficient data source selection with theoretical guarantees. We prove that data source selection in federated learning is a monotone submodular maximization problem and propose FDSS, an efficient algorithm with a constant approximate ratio. Furthermore, we extend FDSS to FDSS-d for dynamic data source selection. Extensive experiments on CIFAR10 and CIFAR100 validate the efficiency and effectiveness of our algorithms.