headshot
headshot

Giorgos Bouritsas

I am a machine learning scientist, a postdoctoral fellow at the Archimedes AI unit and the University of Athens and an adjunct lecturer at NCSR Demokritos and the University of Athens. Additionally, I am a founding member of Visible Machiines, an Athens-based non-profit organisation that researches and informs on the social dimensions of Artificial Intelligence. I obtained my PhD in computer science from Imperial College London, and my MEng in electrical and computer engineering from the National Technical University of Athens. Previously, I spent time at Google Deepmind, École Polytechnique Fédérale de Lausanne , KU Leuven, NCSR Demokritos and Universitat Politècnica de Catalunya. I conduct basic and applied research on several machine learning topics, particularly within Geometric/Graph Deep Learning, where I design and theoretically analyse data-driven methodologies for geometric and symmetric data, such as complex networks, physical systems, 3D objects and weight spaces. Additionally, I studiy AI from a sociotechnical angle, with a particular focus on algorithmic auditing and AI interpretability. My work has been published in leading conferences (NeurIPS, ICML, CVPR, ICCV, ECCV) and journals (TPAMI), while I regularly engage in educational activities and academic service.

Scientific interests

  • Graph neural networks
  • Geometric deep learning
  • Weight space learning
  • Social impact of AI
  • AI auditing
  • Generative models
  • ML for biology/chemistry
News:
  • Nov 2025 New research grant: H.F.R.I. research project for postdoctoral researchers (Principal Investigator): "NNs as Architects (ARCHNETS)", start-end date: March 2026-March 2028
  • Oct 2025 New graduate course: Machine Learning at the MSc Data Science and Information Technologies, Department of Informatics, UoA
  • July 2025 Visible Machines, our non-profit organisation has been launched.
  • Mar 2025 Weight space learning workshop accepted papers announced.
  • Dec 2024 Our workshop proposal on Neural Network Weights as a New Data Modality got accepted at ICLR 2025, Singapore, 27 April 2025. Stay tuned for the call for papers.
  • Sep 2024 Our paper Scale Equivariant Graph Metanetworks has been accepted at NeurIPS 2024 for oral presentation.
  • Apr 2024 Our paper Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses has been accepted at ICML 2024.
  • Jan 2024 This spring semester I will be teaching Deep Learning at the Msc in AI, NCSR Demokritos.
  • Jul 2023 I am starting a postdoc at Archimedes AI and I will be also affiliated with the department of informatics, UoA.
  • Apr 2023 I have successfully defended my PhD Thesis.

Selected Publications

Teaching / Supervision

Postgraduate

AI & Society

Service

Academic Community : ELLIS society member.
Reviewer :
  • NeurIPS ’20,’21*,’22, ’23, ’24*
  • ICLR’22,’24,’25
  • ICML’22*,’23,’24*, '25
  • LoG’22,’23*
  • ICASSP’23
  • TMLR, TPAMI, Sig. Proc., Comput. Graph. Forum.
∗outstanding reviewer

Contact

Giorgos Bouritsas, PhD
Machine Learning Postdoctoral fellow,
Archimedes AI Unit / Athena RC
Department of Informatics and Telecommunications, University of Athens
Location:
  • Room I13
  • Department of Informatics and Telecommunications,
  • National and Kapodistrian University of Athens, Panepistimioupolis, Ilissia, GR-15784 Athens, Greece