A Systematic Evaluation of Node Embedding Robustness
This work addresses the vulnerability of node embedding methods to data perturbations, which is crucial for applications in network analysis and machine learning, though it is incremental in nature.
The paper systematically evaluates the robustness of node embedding methods to random and adversarial poisoning attacks, finding that node classification is more impacted than network reconstruction, with degree-based and label-based attacks being the most damaging.
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.