The NCC Montenegro team at the University of Montenegro (UoM) regularly meets and collaborates with various research groups within the university. In this way, they stay updated on new research projects, emerging research directions, and especially the topics pursued by young researchers. As a result, the need for high-performance computing (HPC) resources has been identified for the master’s research conducted by two research assistants at the Faculty of Electrical Engineering, UoM, led by Assistant professor Miloš Brajović.
Their research deals with Graph Neural Networks (GNNs), with a particular focus on data representation, interpretability and scalability for complex scientific datasets. GNNs have demonstrated remarkable potential in modeling relational and structured data across various domains, including physics, chemistry, biology and computer vision. However, despite their predictive power, their “black-box” nature poses challenges in terms of explainability and trustworthiness, especially in critical applications such as scientific discovery and engineering.
To benchmarking state-of-the-art GNN architectures, evaluate their performance and scalability, and develop and test new GNN models and interpretability techniques for graph-based applications, these two researchers will require access to HPC resources. Therefore, the NCC Montenegro team supported them in preparing and submitting an application for the Development call to gain access to the Leonardo HPC. As a result, they got access to the Leonardo Booster partition, securing 4,500 node hours for their research.
