Graph Neural Network Encoding for Community Detection in Attribute Networks

TL;DR

This paper introduces a novel graph neural network encoding method combined with a multiobjective evolutionary algorithm to improve community detection in complex attribute networks, demonstrating superior performance and smoother fitness landscapes.

Contribution

It proposes a new GNN encoding approach integrated with MOEA for community detection, enhancing solution quality and landscape smoothness compared to existing methods.

Findings

The proposed algorithm outperforms well-known evolutionary and non-evolutionary algorithms.

The encoding method results in smoother fitness landscapes, facilitating optimization.

Experimental results validate the effectiveness of the new approach across various network types.

Abstract

In this paper, we first propose a graph neural network encoding method for multiobjective evolutionary algorithm to handle the community detection problem in complex attribute networks. In the graph neural network encoding method, each edge in an attribute network is associated with a continuous variable. Through non-linear transformation, a continuous valued vector (i.e. a concatenation of the continuous variables associated with the edges) is transferred to a discrete valued community grouping solution. Further, two objective functions for single- and multi-attribute network are proposed to evaluate the attribute homogeneity of the nodes in communities, respectively. Based on the new encoding method and the two objectives, a multiobjective evolutionary algorithm (MOEA) based upon NSGA-II, termed as continuous encoding MOEA, is developed for the transformed community detection problem with continuous decision variables. Experimental results on single- and multi-attribute networks with different types show that the developed algorithm performs significantly better than some well-known evolutionary and non-evolutionary based algorithms. The fitness landscape analysis verifies that the transformed community detection problems have smoother landscapes than those of the original problems, which justifies the effectiveness of the proposed graph neural network encoding method.