RobustECD: Enhancement of Network Structure for Robust Community Detection

Jiajun Zhou, Zhi Chen, Min Du, Lihong Chen, Shanqing Yu, Guanrong Chen, Qi Xuan

Abstract: Community detection, which focuses on clustering vertex interactions, plays a significant role in network analysis. However, it also faces numerous challenges like missing data and adversarial attack. How to further improve the performance and robustness of community detection for real-world networks has raised great concerns. In this paper, we explore <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">robust community detection</i> by enhancing network structure, with two generic algorithms presented: one is named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">robust community detection via genetic algorithm</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RobustECD-GA</i> ), in which the modularity and the number of clusters are combined in a fitness function to find the optimal structure enhancement scheme; the other is called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">robust community detection via similarity ensemble</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">RobustECD-SE</i> ), integrating multiple information of community structures captured by various vertex similarities, which scales well on large-scale networks. Comprehensive experiments on real-world networks demonstrate, by comparing with two traditional enhancement strategies, that the new methods help six representative community detection algorithms achieve more significant performance improvement. Moreover, experiments on the corresponding adversarial networks indicate that the new methods could also optimize the network structure to a certain extent, achieving stronger robustness against adversarial attack.