I am currently a research engineer at the Interdisciplinary Institute of Innovation (i3) at Télécom Paris. My main activities involve designing new computational social science tools, and studying sociotechnical aspects of artificial intelligence, in particular in the context of climate change.
Before that, I was a PhD Candidate in computer science at Institut Polytechnique de Paris , under the supervision of Thomas Bonald (LTCI – Information Processing and Communications Laboratory, Télécom Paris) and Tiphaine Viard, (i3). During my PhD, I adopted an interdisciplinary perspective to study Artificial Intelligence (AI). On one hand, I investigated how graphs can enhance the efficiency and scalability of AI techniques. On the other hand, I approached AI as an object of study, providing insights into its ethical and environmental implications.
My research interests include:
- Environmental impacts of AI (and the whole digital sector)
- Complex networks
- Graph learning algorithms
- Digital science and technology studies
- Computational social sciences
You can find more information about my teaching activities. In 2024 and 2025, I am also participating in one of the F93 association projects, which aims to promote an openness to science and technology, among others, to middle school students. Specifically, this project adresses algorithms and their biases.
Research
PUBLICATIONS
Graph Neural Networks: The Surprising Superiority of Logistic Regression
Simon Delarue, Thomas Bonald, Tiphaine Viard
[Under review]
Link Prediction Without Learning
Simon Delarue, Thomas Bonald, Tiphaine Viard
European Conference on Artificial Intelligence, 2024
[code] [paper]
Evaluating Graph-Based Explanations for AI-Based Recommender Systems
Simon Delarue, Astrid Bertrand, Tiphaine Viard
Preprint
[paper]
Mapping AI Ethics: a Meso-Scale Analysis of Charters and Manifestos
Mélanie Gornet, Simon Delarue, Maria Boritchev, Tiphaine Viard
ACM Conference on Fairness, Accountability and Transparency, 2024
[material] [paper]
Interpretive Flexibility in Data Science and Artificial Intelligence
Tiphaine Viard, Mélanie Gornet, Simon Delarue
Undone Computer Science Conference, 2024
[paper]
Sparse Graph Neural Networks with Scikit-network
Simon Delarue, Thomas Bonald
International Conference on Complex Networks and their Applications, 2023
[code] [paper]
Unexpected Attributed Subgraphs: a Mining Algorithm
Simon Delarue, Tiphaine Viard, Jean-Louis Dessalles
IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, 2023
[code] [paper]
TALKS
HI!PARIS READING GROUP ON GRAPH NEURAL NETWORKS, 2022
Representation Learning on large graphs (with Thomas Bonald)
[ressource material]
INSTITUT POLYTECHNIQUE DE PARIS DOCTORAL SCHOOL DAY, 2022
Unexpected attributed subgraphs: a mining algorithm (Best poster award in the field of Computing, Data and Artificial Intelligence)
[poster]
HI!PARIS SUMMER SCHOOL, 2022
Sparse Graph Neural Networks (Best poster award)
[poster]