Centralization Problem for Opinion Convergence in Decentralized Networks

Yiping Liu, Jiamou Liu, Bakh Khoussainov, Miao Qiao, Bo Yan, Mengxiao Zhang

Abstract: This paper presents a novel perspective on the relationship between decentralization, a prevalent characteristic of multi-agent systems, and centralization, which involves imposing central control to achieve system-level objectives. Specifically, within the context of a networked opinion dynamic model, we introduce and discuss a framework for centralization. In this framework, a decentralized network consists of autonomous agents and a dynamic, unknown social structure. Centralization involves appointing specific agents in the network as access units, responsible for providing information and exerting influence within their local environments. We focus on centralization for the DeGroot model of opinion dynamics, aiming to achieve opinion convergence with the minimum number of access units. To accomplish this, we demonstrate that selecting access units to form a dominating set is crucial. Moreover, we propose algorithms based on a new local algorithmic framework called prowling to facilitate this process. Through systematic experiments conducted on both real-world and synthetic networks, we validate our algorithm and show its superiority over benchmark methods.