headshot
headshot

Giorgos Bouritsas

I am a machine learning scientist, a postdoctoral fellow and an adjunct lecturer at the Department of Informatics, University of Athens and at the Archimedes AI unit/Athena RC. Additionally, I am a founding member of Visible Machines, 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 study 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

  • AI auditing - transparency, interpretability, trustworthiness
  • Societal impact of AI
  • Weight space learning
  • Geometric deep learning
  • Generative models & self-supervised learning
  • ML for biology/chemistry
News:

Selected Publications

Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance

Ioannis Kalogeropoulos, Giorgos Bouritsas, Yannis Panagakis

ICLR'26 AFAA Workshop

Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search

Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis

International Conference on Machine Learning 2026

Scale Equivariant Graph Metanetworks

Ioannis Kalogeropoulos*, Giorgos Bouritsas*, Yannis Panagakis

Neural Information Processing Systems 2024

Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses

Panagiotis Koromilas*, Giorgos Bouritsas*, Theodoros Giannakopoulos, Mihalis Nicolaou, Yannis Panagakis

International Conference on Machine Learning 2024

Towards generalizable particle picking in Cryo-EM images by leveraging Masked AutoEncoders

Andreas Zamanos, Panagiotis Koromilas, Giorgos Bouritsas, Panagiotis L Kastritis, Yannis Panagakis

Cell reports methods, ICML'24 AccMLBio Workshop

Partition and Code: learning how to compress graphs

Giorgos Bouritsas, Andreas Loukas, Nikolaos Karalias, Michael M Bronstein

Neural Information Processing Systems 2021

Deep polynomial neural networks

Grigorios G Chrysos, Stylianos Moschoglou, Giorgos Bouritsas, Jiankang Deng, Yannis Panagakis, Stefanos Zafeiriou

IEEE Transactions on Pattern Analysis and Machine Intelligence 2021

Improving graph neural network expressivity via subgraph isomorphism counting

Giorgos Bouritsas, Fabrizio Frasca, Stefanos Zafeiriou, Michael M Bronstein

IEEE Transactions on Pattern Analysis and Machine Intelligence 2022

Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation

Giorgos Bouritsas, Sergiy Bokhnyak, Stylianos Ploumpis, Michael Bronstein, Stefanos Zafeiriou

International Conference on Computer Vision (ICCV) 2019

Pi-nets: Deep Polynomial Neural Networks

Grigorios G Chrysos, Stylianos Moschoglou, Giorgos Bouritsas, Jiankang Deng, Yannis Panagakis, Stefanos Zafeiriou

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2020

AI & Society

Visible Machines founding member:

  • AI auditing: data-driven NN auditing/editing via metanetworks (regulations, fairness, pruning, etc.), automated bias detection in foundation models (e.g. text-to-image).
  • Social engagement: AI news & science communication.

Articles

Bias, Transparency, and Accountability of AI Systems. Op-ed on the necessity of technical audits of AI algorithms. Read more on Visible Machines

Teaching / Supervision

Postgraduate

Service

Academic Community: ELLIS society member.

Workshop organiser: ICLR'25 workshop on weight space learning

Reviewer: NeuIPS, ICLR, ICML, LoG, TPAMI, TMLR, etc.

Contact

Giorgos Bouritsas, PhD

Machine Learning Postdoctoral fellow,

Archimedes AI Unit / Athena RC

Department of Informatics and Telecommunications, University of Athens

g.bouritsas@athenarc.gr

Location:

Room A14,

Department of Informatics and Telecommunications,

National and Kapodistrian University of Athens, Panepistimioupolis, Ilissia, GR-15784 Athens, Greece