In recent years, there has been a growing demand for renewable energy sources, which are
inherently associated with a decentralized distribution and dependent on weather …

Objectives: Graph representation learning (GRL) has emerged as a pivotal field that has
contributed significantly to breakthroughs in various fields, including biomedicine. The …

Vulnerability detectors based on deep learning (DL) models have proven their effectiveness
in recent years. However, the shroud of opacity surrounding the decision-making process of …

Graph neural networks (GNNs) are powerful tools on graph data. However, their predictions
are mis-calibrated and lack interpretability, limiting their adoption in critical applications. To …

Graph Neural Networks (GNNs) have received considerable attention on graph-structured
data learning for a wide variety of tasks. The well-designed propagation mechanism, which …

The last decade has witnessed a huge growth in the development of deep neural network-
based techniques for graphs and Graph Neural Networks (GNNs) have proven to be the …

Heterogeneous graph neural networks (HGNNs) excel in capturing graph topology and
structural information. However, they are ineffective in processing the textual components …

This thesis addresses the detection of fraud in health insurance reimbursement claims using
attributed graphs. The objective is to develop effective methods to identify anomalies, even …