Government
An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints
Mehmet Fatih Sahin, Armin eftekhari, Ahmet Alacaoglu, Fabian Latorre, Volkan Cevher
We propose a practical inexact augmented Lagrangian method (iALM) for noncon-vex problems with nonlinear constraints.
Appendices to " GNNGUARD: Defending Graph Neural Networks against Adversarial Attacks "
Results are shown in Table 6. T able 6: Defense performance (multi-class classification accuracy) against influence targeted attacks. Results are shown in Table 7. To evaluate how harmful non-targeted attacks can be for GNNs, we first give results without attack and under attack (without defense), i.e., "Attack" vs. "No Attack" columns The accuracy of even the strongest GNN is reduced by 18.7% on GNN if the defender is used on clean, non-attacked graphs. GNNs when they are attacked.
Defending Graph Neural Networks against Adversarial Attacks
However, recent findings indicate that small, unnoticeable perturbations of graph structure can catastrophically reduce performance of even the strongest and most popular Graph Neural Networks (GNNs).
Learnability with Indirect Supervision Signals
Learning from indirect supervision signals is important in real-world AI applications when, often, gold labels are missing or too costly.
Supplementary Material for " Adversarial Learning for Robust Deep Clustering " Xu Y ang 1 Cheng Deng 1 Kun Wei 1 Junchi Y an 2
This supplementary material includes two sections i.e., details of baselines and descriptions of We select some samples with inconsistent clustering results before and after the attack strategy.
Matrix Completion with Hierarchical Graph Side Information
We develop a universal, parameter-free, and computationally efficient algorithm that starts with hierarchical graph clustering and then iteratively refines estimates both on graph clustering and matrix ratings.
