Mao Wang
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundaries across diverse graph connectivity types.
GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundaries across diverse graph connectivity types.
Papers
GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks
Canyixing Cui, Tao Wu, Xingping Xian, Xiao-Ke Xu +2 more
GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundar…