Graph neural networks for graphs with heterophily: A survey
Recent years have witnessed fast developments of graph neural networks (GNNs) that have
benefited myriads of graph analytic tasks and applications. In general, most GNNs depend …
benefited myriads of graph analytic tasks and applications. In general, most GNNs depend …
Graph neural network operators: a review
Abstract Graph Neural Networks (GNN) is one of the promising machine learning areas in
solving real world problems such as social networks, recommender systems, computer …
solving real world problems such as social networks, recommender systems, computer …
Adversarial robustness in graph neural networks: A Hamiltonian approach
Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those
that affect both node features and graph topology. This paper investigates GNNs derived …
that affect both node features and graph topology. This paper investigates GNNs derived …
Mitigating Emergent Robustness Degradation while Scaling Graph Learning
Although graph neural networks have exhibited remarkable performance in various graph
tasks, a significant concern is their vulnerability to adversarial attacks. Consequently, many …
tasks, a significant concern is their vulnerability to adversarial attacks. Consequently, many …
IDEA: Invariant Defense for Graph Adversarial Robustness
Despite the success of graph neural networks (GNNs), their vulnerability to adversarial
attacks poses tremendous challenges for practical applications. Existing defense methods …
attacks poses tremendous challenges for practical applications. Existing defense methods …
Self-Guided Robust Graph Structure Refinement
Recent studies have revealed that GNNs are vulnerable to adversarial attacks. To defend
against such attacks, robust graph structure refinement (GSR) methods aim at minimizing …
against such attacks, robust graph structure refinement (GSR) methods aim at minimizing …
SAGMAN: Stability Analysis of Graph Neural Networks on the Manifolds
Modern graph neural networks (GNNs) can be sensitive to changes in the input graph
structure and node features, potentially resulting in unpredictable behavior and degraded …
structure and node features, potentially resulting in unpredictable behavior and degraded …
Grove: Ownership verification of graph neural networks using embeddings
Graph neural networks (GNNs) have emerged as a state-of-the-art approach to model and
draw inferences from large scale graph-structured data in various application settings such …
draw inferences from large scale graph-structured data in various application settings such …
Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study
In this work, we rigorously investigate the robustness of graph neural fractional-order
differential equation (FDE) models. This framework extends beyond traditional graph neural …
differential equation (FDE) models. This framework extends beyond traditional graph neural …
Graph Adversarial Diffusion Convolution
This paper introduces a min-max optimization formulation for the Graph Signal Denoising
(GSD) problem. In this formulation, we first maximize the second term of GSD by introducing …
(GSD) problem. In this formulation, we first maximize the second term of GSD by introducing …