Skip to Main content Skip to Navigation
Journal articles

Communication Efficient Decentralized Learning Over Bipartite Graphs

Abstract : In this paper, we propose a communication-efficiently decentralized machine learning framework that solves a consensus optimization problem defined over a network of inter-connected workers. The proposed algorithm, Censored and Quantized Generalized GADMM (CQ-GGADMM), leverages the worker grouping and decentralized learning ideas of Group Alternating Direction Method of Multipliers (GADMM), and pushes the frontier in communication efficiency by extending its applicability to generalized network topologies, while incorporating link censoring for negligible updates after quantization. We theoretically prove that CQ-GGADMM achieves the linear convergence rate when the local objective functions are strongly convex under some mild assumptions. Numerical simulations corroborate that CQ-GGADMM exhibits higher communication efficiency in terms of the number of communication rounds and transmit energy consumption without compromising the accuracy and convergence speed, compared to the censored decentralized ADMM, and the worker grouping method of GADMM.
Document type :
Journal articles
Complete list of metadata
Contributor : DELPHINE LE PIOLET Connect in order to contact the contributor
Submitted on : Thursday, November 25, 2021 - 9:54:53 AM
Last modification on : Thursday, November 25, 2021 - 9:54:54 AM

Links full text




Chaouki Ben Issaid, Anis Elgabli, Jihong Park, Mehdi Bennis, Merouane Debbah. Communication Efficient Decentralized Learning Over Bipartite Graphs. IEEE Transactions on Wireless Communications, Institute of Electrical and Electronics Engineers, 2021, pp.1-1. ⟨10.1109/TWC.2021.3126859⟩. ⟨hal-03448311⟩



Record views