Making Communities Show Respect for Order

TL;DR

This paper introduces a community detection algorithm for directed acyclic graphs that respects their order and groups similar nodes, outperforming standard methods in distinguishing node origins.

Contribution

The paper presents a novel community detection algorithm inspired by bibliometric similarity measures that respects DAG order and effectively groups nodes by origin.

Findings

The algorithm performs well on artificial and real networks.

It distinguishes node origins better than standard methods.

Produces different communities than hierarchical layering algorithms.

Abstract

In this work we give a community detection algorithm in which the communities both respects the intrinsic order of a directed acyclic graph and also finds similar nodes. We take inspiration from classic similarity measures of bibliometrics, used to assess how similar two publications are, based on their relative citation patterns. We study the algorithm's performance and antichain properties in artificial models and in real networks, such as citation graphs and food webs. We show how well this partitioning algorithm distinguishes and groups together nodes of the same origin (in a citation network, the origin is a topic or a research field). We make the comparison between our partitioning algorithm and standard hierarchical layering tools as well as community detection methods. We show that our algorithm produces different communities from standard layering algorithms.