Probabilistic Node Selection for Federated Learning with Heterogeneous Data in Mobile Edge

Abstract

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 global and local objectives, making the FL model slow to converge. In this paper, we proposed the 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 Probabilistic Node Selection 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. Experimental results demonstrate the effectiveness of FedPNS in accelerating the FL convergence rate, as compared to FedAvg with random node selection.