Robust graph embedding via Attack-aid Graph Denoising

The quality of graphs directly affects the result of graph embedding since most existing models are vulnerable and highly sensitive to harmful/missing edges and imperceptible attacks. In this study, we propose a new robust graph embedding approach from a different point of view: Attack-aid Graph Denoising (AGD). AGD mitigates the impact of harmful and missing edges by leveraging adversarial attacks. Initially, AGD generates some auxiliary attacks on the topology by investigating their harm to classification accuracy. Subsequently, we derive a denoised adjacency matrix by removing these similar harmful edges and supplementing missing edges with flipping operations. Finally, we further extract the knowledge of topology to eliminate the influence of remaining harmful edges on the final embedding with Kullback-Leibler divergence. Extensive experiments have demonstrated that AGD not only shows its superiority over many state-of-theart algorithms on the classification tasks but is also robust to various attacks.