Decentralized learning for wireless communications and networking

TL;DR

This paper explores decentralized learning algorithms for wireless networks, enabling local data processing and global inference without extensive data exchange, demonstrated through various wireless communication case studies.

Contribution

It introduces a generic decentralized learning framework using ADMM, tailored for graph-valued data in wireless networks, with practical case studies illustrating its effectiveness.

Findings

Effective decentralized learning without sharing raw data

Application to wireless sensor networks and spectrum management

Maintains performance comparable to centralized methods

Abstract

This chapter deals with decentralized learning algorithms for in-network processing of graph-valued data. A generic learning problem is formulated and recast into a separable form, which is iteratively minimized using the alternating-direction method of multipliers (ADMM) so as to gain the desired degree of parallelization. Without exchanging elements from the distributed training sets and keeping inter-node communications at affordable levels, the local (per-node) learners consent to the desired quantity inferred globally, meaning the one obtained if the entire training data set were centrally available. Impact of the decentralized learning framework to contemporary wireless communications and networking tasks is illustrated through case studies including target tracking using wireless sensor networks, unveiling Internet traffic anomalies, power system state estimation, as well as spectrum cartography for wireless cognitive radio networks.