A Systematic Evaluation of Node Embedding Robustness

TL;DR

This paper systematically evaluates the robustness of various node embedding methods against random and adversarial attacks, revealing their vulnerabilities and the factors influencing attack effectiveness.

Contribution

It provides a comprehensive empirical assessment of node embedding robustness, comparing multiple attack strategies and analyzing their impact on downstream tasks.

Findings

Node classification is more affected by attacks than network reconstruction.

Degree-based and label-based attacks are most damaging.

Label heterophily influences attack performance significantly.

Abstract

Node embedding methods map network nodes to low dimensional vectors that can be subsequently used in a variety of downstream prediction tasks. The popularity of these methods has grown significantly in recent years, yet, their robustness to perturbations of the input data is still poorly understood. In this paper, we assess the empirical robustness of node embedding models to random and adversarial poisoning attacks. Our systematic evaluation covers representative embedding methods based on Skip-Gram, matrix factorization, and deep neural networks. We compare edge addition, deletion and rewiring attacks computed using network properties as well as node labels. We also investigate the performance of popular node classification attack baselines that assume full knowledge of the node labels. We report qualitative results via embedding visualization and quantitative results in terms of downstream node classification and network reconstruction performances. We find that node classification results are impacted more than network reconstruction ones, that degree-based and label-based attacks are on average the most damaging and that label heterophily can strongly influence attack performance.