Unsupervised Adversarially-Robust Representation Learning on Graphs
This work tackles the problem of adversarial robustness in unsupervised graph representation learning, which is crucial for deploying these models in real-world applications where data integrity is a concern, particularly for those relying on pre-trained graph models.
This paper addresses the lack of adversarial robustness in unsupervised graph representation learning. The authors propose an unsupervised defense technique that quantifies graph representation vulnerability (GRV) using mutual information and optimizes graph representations to balance expressiveness and robustness. Their method improves robustness against adversarial attacks on three downstream tasks (node classification, link prediction, and community detection) by an average of +16.5% compared to existing methods, without using labels or task-specific information.
Unsupervised/self-supervised pre-training methods for graph representation learning have recently attracted increasing research interests, and they are shown to be able to generalize to various downstream applications. Yet, the adversarial robustness of such pre-trained graph learning models remains largely unexplored. More importantly, most existing defense techniques designed for end-to-end graph representation learning methods require pre-specified label definitions, and thus cannot be directly applied to the pre-training methods. In this paper, we propose an unsupervised defense technique to robustify pre-trained deep graph models, so that the perturbations on the input graph can be successfully identified and blocked before the model is applied to different downstream tasks. Specifically, we introduce a mutual information-based measure, \textit{graph representation vulnerability (GRV)}, to quantify the robustness of graph encoders on the representation space. We then formulate an optimization problem to learn the graph representation by carefully balancing the trade-off between the expressive power and the robustness (\emph{i.e.}, GRV) of the graph encoder. The discrete nature of graph topology and the joint space of graph data make the optimization problem intractable to solve. To handle the above difficulty and to reduce computational expense, we further relax the problem and thus provide an approximate solution. Additionally, we explore a provable connection between the robustness of the unsupervised graph encoder and that of models on downstream tasks. Extensive experiments demonstrate that even without access to labels and tasks, our model is still able to enhance robustness against adversarial attacks on three downstream tasks (node classification, link prediction, and community detection) by an average of +16.5% compared with existing methods.