Giannis Nikolentzos

Giannis Nikolentzos is an Assistant Professor at the Department of Informatics and Telecommunications, University of Peloponnese. His research focuses on graph representation learning, machine learning, and artificial intelligence. Prior to this role, he was a postdoctoral researcher at Ecole Polytechnique and completed his PhD in Computer Science at Athens University of Economics and Business, advised by Michalis Vazirgiannis. He holds an MSc in Artificial Intelligence from the University of Southampton and a Diploma in Electrical and Computer Engineering from the University of Patras.

His research interests include learning on graphs, graph mining, and machine learning applications in healthcare and social networks. He has contributed to advancements in graph neural networks (GNNs), adversarial attacks on GNNs, and synthetic data generation using variational graph autoencoders.

Recent Publications highlight trends in understanding GNN representations, adversarial robustness, and graph reasoning with large language models. His work has been presented at top conferences like NeurIPS, ICML, and ICLR.

Nikolentzos has developed the Grakel Python library for graph kernels and contributed to open-source tools like the repository for 'What Do GNNs Actually Learn?' which includes implementation details, datasets (e.g., IMDB-BINARY), and dependencies such as PyTorch and NetworkX.