Network Entropy based on Cluster Expansion on Motifs for Undirected Graphs

TL;DR

This paper introduces a novel approach to analyze network structure by applying statistical mechanics to motifs, deriving entropy measures from a partition function, and demonstrating their correlation with network changes in real-world datasets.

Contribution

It develops a new method to compute motif-based entropy using cluster expansion and partition functions, linking network motifs to thermodynamic quantities.

Findings

Motif entropy correlates with network structural changes.

The method applies to synthetic and real-world networks.

Motif entropy reflects information processing functions in networks.

Abstract

The structure of the network can be described by motifs, which are subgraphs that often repeat themselves. In order to understand the structure of network motifs, it is of great importance to study subgraphs from the perspective of statistical mechanics. In this paper, we use clustering extensions in statistical physics to solve the problem of using motifs as network primitives. By projecting the network motifs to clusters in the gas model, we develop the partition function of the network, which enables us to calculate global thermodynamic quantities, such as energy, entropy, and vice versa. Then, we give the analytic expressions of the number of specific types of motifs and calculate their correlated entropy. We conduct algebraic experiments on datasets, both synthetic and in real life, and evaluate the qualitative and quantitative characterization of motif entropy derived from the partition function. Our findings show that the motif entropy of networks in real life, for instance, financial and stock market networks, is of high correlation to the change of network structure. Hence, our findings are consistent with recent studies about the similar topic that network motifs can be represented as basic elements of well-defined information processing functions.