Adaptive Task Allocation for Mobile Edge Learning

Abstract

This paper aims to establish a new optimization paradigm to efficiently execute distributed learning tasks on wireless edge nodes with heterogeneous computing and communication capacities. We will refer to this new paradigm as “Mobile Edge Learning (MEL)”. The problem of adaptive task allocation for MEL is considered in this paper with the aim to maximize the learning accuracy, while guaranteeing that the total times of data distribution/aggregation over heterogeneous channels, and local computation on heterogeneous nodes, are bounded by a preset duration. The problem is first formulated as a quadratically-constrained integer linear problem. Being NP-hard, the paper relaxes it into a non-convex problem over real variables. We then propose a solution based on deriving analytical upper bounds on the optimal solution of this relaxed problem using KKT conditions. The merits of this proposed solution is exhibited by comparing its performances to both numerical approaches and the equal task allocation approach.