A Systematic Evaluation of Node Embedding Robustness

Alexandru Cristian Mara, Jefrey Lijffijt, Stephan Günnemann, Tijl De Bie

Keywords: Robustness, Embeddings, Evaluation, Poison attacks, Node Classification, Network Reconstruction

TL;DR: We provide a systematic evaluation of node embedding robustness to poison attacks on the input networks.

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.

Type Of Submission: Full paper proceedings track submission (max 9 main pages).

Agreement: Check this if you are okay with being contacted to participate in an anonymous survey.

Type Of Submission: Full paper proceedings track submission.

Software: https://github.com/aida-ugent/EvalNE-robustness

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2209.08064/code)