Robustness of graph embedding methods for community detection

TL;DR

This paper evaluates how different graph embedding methods perform in community detection tasks when networks are perturbed, highlighting the varying robustness of methods like node2vec and LLE across different network scenarios.

Contribution

It provides a comparative analysis of the robustness of state-of-the-art graph embedding methods under network perturbations for community detection.

Findings

node2vec and LLE show higher robustness across scenarios

Robustness depends on network size and community strength

Perturbation type influences embedding performance

Abstract

This study investigates the robustness of graph embedding methods for community detection in the face of network perturbations, specifically edge deletions. Graph embedding techniques, which represent nodes as low-dimensional vectors, are widely used for various graph machine learning tasks due to their ability to capture structural properties of networks effectively. However, the impact of perturbations on the performance of these methods remains relatively understudied. The research considers state-of-the-art graph embedding methods from two families: matrix factorization (e.g., LE, LLE, HOPE, M-NMF) and random walk-based (e.g., DeepWalk, LINE, node2vec). Through experiments conducted on both synthetic and real-world networks, the study reveals varying degrees of robustness within each family of graph embedding methods. The robustness is found to be influenced by factors such as network size, initial community partition strength, and the type of perturbation. Notably, node2vec and LLE consistently demonstrate higher robustness for community detection across different scenarios, including networks with degree and community size heterogeneity. These findings highlight the importance of selecting an appropriate graph embedding method based on the specific characteristics of the network and the task at hand, particularly in scenarios where robustness to perturbations is crucial.