Chrysoula Kosma
Scholar

Chrysoula Kosma

Google Scholar ID: 62TGUbgAAAAJ
ENS Paris-Saclay
Deep LearningTime Series
Citations & Impact
All-time
Citations
58
 
H-index
4
 
i10-index
3
 
Publications
8
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • Paper “Time Series Representations with Hard-Coded Invariances” accepted to ICML 2025
  • Paper “The Signed Two-Space Proximity Model for Learning Representations in Protein-Protein Interaction Networks” accepted for publication at OUP Bioinformatics Journal
  • Paper “Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings” to be presented as a poster in AISTATS 2025, Thailand
  • Paper “Neural Ordinary Differential Equations for Modeling Epidemic Spreading” presented at ICLR 2024 and published in Transactions on Machine Learning (TMLR) journal, awarded with Featured Certification
  • Paper “TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting” accepted at The 12th International Conference on Complex Networks and their Applications, 2023, Menton Riviera, France
Background
  • ML Researcher currently working at Centre Borelli, ENS Paris-Saclay. Passionate about the efficient and scalable application of ML to real-world problems, particularly involving complex and dynamically evolving data, especially for industrial and engineering applications.
Miscellany
  • Personal interests not mentioned