Coded computing for distributed graph-based semi-supervised learning

Abstract

Semi-supervised learning (SSL) has been applied to many practical applications over the past few years. Recently, distributed graph-based semi-supervised learning (DGSSL) has been shown to have good performance. Current DGSSL algorithms usually have the problems of inefficient graph construction and the straggler effect. This paper proposes a novel coded DGSSL (CDGSSL) to solve these problems. We first provide a novel parallel and distributed solution of matrix completion for efficient graph construction. Then, we develop the CDGSSL algorithm based on coding theory. Specifically, the proposed algorithm consists of two parts separately designed based on the maximum distance separable (MDS) code. In general, the proposed coded distributed algorithm is efficient and straggler tolerant. Moreover, we provide an optimal parameter design for the proposed algorithm. The results of the experiments on the Alibaba Cloud elastic compute service (ECS) demonstrate the superiority of the proposed algorithm.