I am currently a Postdoctoral Researcher at Centre Borelli, École normale supérieure (ENS) Paris-Saclay, working in collaboration with Prof. Laurent Oudre and Prof. Mathilde Mougeot on ML/DL methods for time series, funded under the Industrial Data Analytics and Machine Learning (IDAML) Chair. I am passionate about the efficient and scalable application of ML to solving real-world problems, involving complex and dynamically evolving data, particularly for industrial and engineering applications. In November 2023, I completed my PhD in Computer Science & Machine Learning at École Polytechnique, Institut Polytechnique de Paris, in France. During my PhD, I worked under the supervision of Prof. Michalis Vazirgiannis, at the Dascim Group, focusing on robust deep learning methods for time series data and dynamical systems. In October 2020, I was selected to receive partial funding for my PhD by the IP Paris “PhD theses in Artificial Intelligence” (IA IPP 2020) program, provided by ANR. Before this, I obtained a 5-year joint diploma (BSc & MSc equivalent) in Electrical and Computer Engineering from National Technical University of Athens (NTUA), Greece.

News

• 2025/05/01: Exciting News: Our paper “Time Series Representations with Hard-Coded Invariances” with Thibaut Germain and Laurent Oudre, has been accepted to ICML 2025! Check the paper here and our official code implementation here.
• 2025/03/19: Very happy for our paper “The Signed Two-Space Proximity Model for Learning Representations in Protein-Protein Interaction Networks”, with Nikolaos Nakis, Anastasia Brativnyk, Michalis Chatzianastasis, Iakovos Evdaimon & Michalis Vazirgiannis, that is accepted for publication at the OUP Bioinformatics Journal! Paper
• 2025/01/22: Excited that our work “Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings” with Nikolaos Nakis, Giannis Nikolentzos, Michalis Chatzianastasis, Iakovos Evdaimon & Michalis Vazirgiannis will be presented as a poster in AISTATS 2025, in Thailand! Please find the preprint here.
• 2024/05: We presented our TMLR paper “Neural Ordinary Differential Equations for Modeling Epidemic Spreading” in Vienna at ICLR 2024! The poster can be found here.
• 2023/10/04: Our paper with Xu N., Vazirgiannis M., “TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting” has been accepted at The 12th International Conference on Complex Networks and their Applications, 2023, Menton Riviera, France.
• 2023/08/19: Our paper entitled “Neural Ordinary Differential Equations for Modeling Epidemic Spreading” has been accepted for publication at Transactions on Machine Learning (TMLR) journal, awarded with Featured Certification (equivalent to oral/spotlight).
• 2022/10: Happy to serve as a teaching assistant (lab sessions) for the INF554 - Machine and Deep Learning class of 2022-2023 - Computer Science M1 programme, at Ecole Polytechnique!