Info-Clustering: An Efficient Algorithm by Network Information Flow

TL;DR

This paper introduces an efficient info-clustering algorithm based on network information flow, designed to identify communities in social or biological networks by leveraging graphical dependency structures learned from data.

Contribution

It presents a novel clustering method that utilizes a parametric max-flow algorithm within the info-clustering framework, specifically tailored for graphical dependency structures.

Findings

Efficient community detection in networks.

Applicable to social and biological systems.

Leverages data-driven dependency structures.

Abstract

Motivated by the fact that entities in a social network or biological system often interact by exchanging information, we propose an efficient info-clustering algorithm that can group entities into communities using a parametric max-flow algorithm. This is a meaningful special case of the info-clustering paradigm where the dependency structure is graphical and can be learned readily from data.