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 …

Adversarial examples are inputs to machine learning models that an attacker has
intentionally designed to confuse the model into making a mistake. Such examples pose a …

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 …

Nowadays, graph neural networks (GNN) are the primary machinery to tackle (semi)-
supervised graph classification tasks. The aim here is to predict classes for unlabeled …

To construct an accurate crash prediction model, the road safety performance function
(SPF), which provides a safety guide for the management department, is often used. In …

Graph Neural Networks (GNNs) have demonstrated state-of-the-art performance in various
graph representation learning tasks. Recently, studies revealed their vulnerability to …

We propose a robust randomized indicator method for the reliable detection of eigenvalue
existence within an interval for symmetric matrices A. An indicator tells the eigenvalue …

SGM-PINN is a graph-based importance sampling framework to improve the training efficacy
of Physics-Informed Neural Networks (PINNs) on parameterized problems. By applying a …

Artificial neural networks are prone to being fooled by carefully perturbed inputs which
cause an egregious misclassification. These adversarial attacks have been the focus of …

Given that no existing graph construction method can generate a perfect graph for a given
dataset, graph-based algorithms are invariably affected by the plethora of redundant and …