Node Selection Toward Faster Convergence for Federated Learning on Non-IID Data

• Published in: IEEE transactions on network science and engineering Vol. 9; no. 5; pp. 3099 - 3111
• Main Authors: Wu, Hongda, Wang, Ping
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Agglomeration; Algorithms; Computational modeling; Convergence; Data models; Data retrieval; Elections; fast convergence; Federated learning; mobile edge computing; node selection; Nodes; Predictive models; Probabilistic logic; Servers; Training
• DOI: 10.1109/TNSE.2022.3146399
• ISSN: 2327-4697

Federated Learning (FL) is a distributed learning paradigm that enables a large number of resource-limited nodes to collaboratively train a model without data sharing. The non-independent-and-identically-distributed (non-i.i.d.) data samples invoke discrepancies between the global and local objectives, making the FL model slow to converge. In this paper, we proposed Optimal Aggregation algorithm for better aggregation, which finds out the optimal subset of local updates of participating nodes in each global round, by identifying and excluding the adverse local updates via checking the relationship between the local gradient and the global gradient. Then, we proposed a P robabilistic N ode S election framework ( FedPNS ) to dynamically change the probability for each node to be selected based on the output of Optimal Aggregation . FedPNS can preferentially select nodes that propel faster model convergence. The convergence rate improvement of FedPNS over the commonly adopted Federated Averaging ( FedAvg ) algorithm is analyzed theoretically. Experimental results demonstrate the effectiveness of FedPNS in accelerating the FL convergence rate, as compared to FedAvg with random node selection.