Garnet: Reduced-rank topology learning for robust and scalable graph neural networks
Graph neural networks (GNNs) have been increasingly deployed in various applications that
involve learning on non-Euclidean data. However, recent studies show that GNNs are …
involve learning on non-Euclidean data. However, recent studies show that GNNs are …
Speedup robust graph structure learning with low-rank information
Recent studies have shown that graph neural networks (GNNs) are vulnerable to
unnoticeable adversarial perturbations, which largely confines their deployment in many …
unnoticeable adversarial perturbations, which largely confines their deployment in many …
Graph structure learning for robust graph neural networks
Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs.
However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations …
However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations …
Adversarial defense framework for graph neural network
Graph neural network (GNN), as a powerful representation learning model on graph data,
attracts much attention across various disciplines. However, recent studies show that GNN is …
attracts much attention across various disciplines. However, recent studies show that GNN is …
ERGCN: Data enhancement-based robust graph convolutional network against adversarial attacks
With recent advancements, graph neural networks (GNNs) have shown considerable
potential for various graph-related tasks, and their applications have gained considerable …
potential for various graph-related tasks, and their applications have gained considerable …
Topology attack and defense for graph neural networks: An optimization perspective
Graph neural networks (GNNs) which apply the deep neural networks to graph data have
achieved significant performance for the task of semi-supervised node classification …
achieved significant performance for the task of semi-supervised node classification …
A Simple and Yet Fairly Effective Defense for Graph Neural Networks
Graph Neural Networks (GNNs) have emerged as the dominant approach for machine
learning on graph-structured data. However, concerns have arisen regarding the …
learning on graph-structured data. However, concerns have arisen regarding the …
Cap: Co-adversarial perturbation on weights and features for improving generalization of graph neural networks
Despite the recent advances of graph neural networks (GNNs) in modeling graph data, the
training of GNNs on large datasets is notoriously hard due to the overfitting. Adversarial …
training of GNNs on large datasets is notoriously hard due to the overfitting. Adversarial …
Gnnguard: Defending graph neural networks against adversarial attacks
Deep learning methods for graphs achieve remarkable performance on many tasks.
However, despite the proliferation of such methods and their success, recent findings …
However, despite the proliferation of such methods and their success, recent findings …
Defensevgae: Defending against adversarial attacks on graph data via a variational graph autoencoder
A Zhang, J Ma - arXiv preprint arXiv:2006.08900, 2020 - arxiv.org
Graph neural networks (GNNs) achieve remarkable performance for tasks on graph data.
However, recent works show they are extremely vulnerable to adversarial structural …
However, recent works show they are extremely vulnerable to adversarial structural …