Work

Social Learning Over Weakly Connected Graphs

Year: 2017

Type: article

Abstract: In this paper, we study diffusion social learning over weakly connected graphs. We show that the asymmetric flow of information hinders the learning abilities of certain agents regardless of their local observations. Under some circumstances that we clarify in this paper, a scenario of total influence (or “mind-control”) arises where a set of influential agents ends up shaping the beliefs of noninfluential agents. We derive useful closed-form expressions that characterize this influence, and which can be used to motivate design problems to control it. We provide simulation examples to illustrate the results.

Source: IEEE Transactions on Signal and Information Processing over Networks

DOI: 10.1109/tsipn.2017.2668138

Authors: Hawraa Salami, Bicheng Ying, Ali H. Sayed

Institution: University of California, Los Angeles

Language: English

Topic: Game Theory and Applications

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

Funders: National Science Foundation, Defense Advanced Research Projects Agency

Awards: Online Learning in Big-Data Stream Mining, G7288360644, CIF: Small: Inference over Asymmetric Network and Data Structures