George Panagopoulos
Research Scientist & Principal Investigator
Luxembourg
Summary
👤
Senior🎓
Top SchoolGeorge Panagopoulos is a research scientist and principal investigator based in Luxembourg with a decade of experience at the intersection of graph machine learning, causal inference, and computational biology. He holds a PhD from École Polytechnique and has transitioned academic rigor into industry impact through roles at Amazon and influential open-source contributions, including enhancements to the PyTorch Geometric Temporal library for spatiotemporal modeling. At the University of Luxembourg he secured nearly €830k in competitive funding for projects on graph active learning and structure-aware foundation models for gene perturbation, and designs and teaches graduate courses in graph ML. Known for combining model-level engineering (e.g., adding novel MPNN_LSTM architectures and dataset loaders) with applied science, he bridges theory and practice to push graph-based methods into real-world and biomedical applications.
10 years of coding experience
8 years of employment as a software developer
Master of Science - MS Computer Science, Master of Science - MS Computer Science at University of HoustonDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at École PolytechniqueBachelor's degree Informatics and Telematics, Bachelor's degree Informatics and Telematics at Harokopio
English, Greek, French
Github Skills (7)
pytorch10
lstm10
graph-neural-network10
gnn10
deeplearning-ai9
deep-learning9
python8
Programming languages (1)
Github contributions (5)
benedekrozemberczki/pytorch_geometric_temporal
Mar 2021 - Mar 2021
PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
Role in this project:
ML Engineer
ML EngineerContributions:19 commits, 7 PRs in 20 days
Contributions summary:George primarily contributed to the implementation and modification of machine learning models within the PyTorch Geometric Temporal framework. Their work included adding a new MPNN_LSTM model, adjusting its architecture, and modifying existing components to improve functionality. They also added a dataset loader for an English Covid19 dataset, indicating a focus on applying the framework to spatiotemporal data analysis. Furthermore, adjustments to output representations show iterative refinement in the model's design.
node-embeddingsignalsignal-processingspatio-temporal-analysisgraph-convolution
geopanag/Detecting-Rising-Stars-in-Dynamic-Collaborative-Networks
Dec 2015 - Feb 2019
Contributions:20 commits, 15 pushes in 3 years 2 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.