Giannis (Ioannis) Kalogeropoulos
PhD student (NKUA) & Academic fellow
National and Kapodistrian University of Athens
SHORT BIO
Giannis holds an MEng in Electrical and Computer Engineering from the National Technical University of Athens, focusing on Computer Science. During his studies, he studied a lot of state-of-the-art deep learning techniques and cultivated a strong interest in Geometric Deep Learning. While working on his Diploma Thesis, he employed Graph Neural Networks and incorporated external knowledge for the multimodal task of Visual Dialog.
He has professional and research experience in studying and implementing machine learning models in a wide range of fields. Specifically, as a Machine Learning Engineer, he has worked on Natural Language Processing and Time Series Forecasting problems, employing, among others, pre-trained Language Models. Moreover, he has dove deeper into the MLOps techniques for orchestrating the whole lifecycle of an ML model. Finally, he has published and presented at an IEEE conference his work on Machine Learning and Edge Computing.
RESEARCH INTERESTS
Giannis' research interests lie in the fields of geometric deep learning, multimodal fusion, and computer vision. Specifically, his work will focus on developing graph-based multimodal fusion methods, designing models that respect intra- and cross-modal symmetries and experimenting with cross-modal interactions.
PhD research on 'Learning in Weight Spaces"
Abstract: Weight space learning explores NN parameters as a new data modality. It enables model analysis, synthesis, and parameter generation, offering pathways to automate ML pipelines and unify representations across applications, including neural fields and implicit representations. In our work, we propose ScaleGMN that adapts the MPNN paradigm by incorporating scaling symmetries, achieving state-of-the-art results.
RESEARCH AREAS
