2 papers
cs.LG2020
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs
Jiarong Xu, Yizhou Sun, Xin Jiang +4
Adversarial attacks on graphs have attracted considerable research interests. Existing works assume the attacker is either (partly) aware of the victim model, or able to send queri…
cs.LG2020
Unsupervised Adversarially-Robust Representation Learning on Graphs
Jiarong Xu, Yang Yang, Junru Chen +4
Unsupervised/self-supervised pre-training methods for graph representation learning have recently attracted increasing research interests, and they are shown to be able to generali…