A Triclustering Approach for Time Evolving Graphs

TL;DR

This paper presents a parameter-free triclustering method for time-evolving graphs that automatically segments time and clusters vertices based on evolving edge distributions, aiding exploratory analysis.

Contribution

It introduces a novel, parameter-free three-dimensional co-clustering technique that infers time segments directly from edge distribution evolution, without prior discretization.

Findings

Effective on synthetic datasets demonstrating good segmentation.

Shows potential for exploratory analysis on real-world data.

Automatically infers meaningful time segments and clusters.

Abstract

This paper introduces a novel technique to track structures in time evolving graphs. The method is based on a parameter free approach for three-dimensional co-clustering of the source vertices, the target vertices and the time. All these features are simultaneously segmented in order to build time segments and clusters of vertices whose edge distributions are similar and evolve in the same way over the time segments. The main novelty of this approach lies in that the time segments are directly inferred from the evolution of the edge distribution between the vertices, thus not requiring the user to make an a priori discretization. Experiments conducted on a synthetic dataset illustrate the good behaviour of the technique, and a study of a real-life dataset shows the potential of the proposed approach for exploratory data analysis.