Clustering of temporal nodes profiles in dynamic networks of contacts

TL;DR

This paper introduces a framework for analyzing dynamic networks by clustering temporal node profiles based on their evolving memberships in weighted-rich-clubs, providing deeper insights into temporal network structures.

Contribution

It extends static weighted-rich-clubs analysis to dynamic stream graphs by clustering nodes' temporal profiles, revealing typical patterns in evolving networks.

Findings

Effective clustering of temporal profiles in real-world contact networks.

Enhanced understanding of the temporal structure of dynamic networks.

Abstract

Stream graphs are a very useful mode of representation for temporal network data, whose richness offers a wide range of possible approaches. The various methods aimed at generalising the classical approaches applied to static networks are constantly being improved. In this paper, we describe a framework that extend to stream graphs iterative weighted-rich-clubs characterisation for static networks proposed in [1]. The general principle is that we no longer consider the membership of a node to one of the weighted-rich-clubs for the whole time period, but each node is associated with a temporal profile which is the concatenation of the successive memberships of the node to the weighted-rich-clubs that appear, disappear and change all along the period. A clustering of these profiles gives the possibility to establish a reduced list of typical temporal profiles and so a more in-depth understanding of the temporal structure of the network. This approach is tested on real world data produced by recording the interactions between different students within their respective schools. [1] M. Djellabi, B. Jouve, and F. Amblard. Dense and sparse vertex connectivity in networks. Journal of Complex Networks, 8(3), 2020.