- \n
- Publications<\/a><\/li>\n
- Long CV<\/a> (last update: 23 March 2025)<\/small>\n
\n<\/li>\n<\/ul>\n
Currently<\/strong><\/span><\/h2>\n
Position:<\/strong> Permanent senior researcher at the Centre Giovanni Borelli<\/a>1<\/sup><\/small>, Ecole Normale Sup\u00e9rieure Paris-Saclay (ENS Paris-Saclay), University Paris-Saclay, France<\/a>, and member of the Learning and Information Processing Systems (LIPS) research group2<\/sup><\/small>. ...<\/span>
\n1<\/sup> ex Centre de Math\u00e9matiques et de Leurs Applications (CMLA).
\n2<\/sup> ex Machine Learning and Massive Data Analysis (MLMDA).<\/div><\/small><\/p>\nResearch interests & focus: <\/strong>Broad interest in statistical ML. Coordinator of the ML on Graphs<\/strong><\/em> research theme.<\/p>\n
Research initiatives:<\/strong> Member of the Industrial Data Analytics and Machine Learning Chair<\/a>, having as industrial partners SNCF<\/a>, CEA<\/a>, Michelin<\/a>. Other Academia-Industry synergies: join probject with RTE<\/a>&SNCF<\/a>, and collaboration with\u00a0EDF<\/a>. —\u00a0Other initiatives: <\/strong>Since 2017, (co-)organizer of the LIPS seminars.<\/p>\n
Past funding:<\/strong> ...<\/span>
In the past, the research position at CMLA had been funded in the past by the MORANE<\/em> project (in collaboration with SNCF railway company) and the SODATECH<\/em> project\u00a0 (funded by the French state). See more details at the Projects<\/a> section.<\/p>\n<\/div>\nCurrent PhD students: <\/strong><\/p>\n
- \n
- Ga\u00ebtan Serr\u00e9<\/a> (~ global optimization)<\/li>\n
- Gwendal Debaussart<\/a> (~ graph representation learning)<\/li>\n
- Eloi Campagne<\/a> (~ time-series forecasting for the energy sector)<\/li>\n
- Gaspard Abel<\/a> (~ machine learning on social interaction networks)<\/li>\n
- Gabriel Singer<\/a> (~ statistical machine learning in uncertainty (imperfect labels))<\/li>\n
- Jean Velluet<\/a> (~ social network analysis on natural resources exploitation (fishery))<\/li>\n<\/ul>\n
Alumni:<\/strong> ...<\/span>
\nPhD students: <\/strong><\/p>\n
- \n
- Alejandro de la Concha Duarte<\/a> (2025)<\/li>\n
- Mathilde Fekom (2021)<\/li>\n
- Batiste Le Bars<\/a> (2021)<\/li>\n
- Kevin Scaman<\/a> (2016)<\/li>\n<\/ul>\n
Post-docs: <\/strong><\/p>\n
- \n
- Harry Sevi<\/a> (2020-2022)<\/li>\n<\/ul>\n
Internships:<\/strong><\/p>\n
- \n
- Master 2<\/strong>\n
- \n
- Mateo Sesia (2014)<\/li>\n
- Xavier Lioneton (2016)<\/li>\n
- Stefano Sarao (2016)<\/li>\n
- Luca Corinzia (2016)<\/li>\n
- Mathilde Fekom (2017)<\/li>\n
- Matteo Neri (2017)<\/li>\n
- Amel Addala (2019)<\/li>\n
- Alexandro de la Concha (2019 MVA)<\/li>\n
- Anthea M\u00e9rida (2019 ENSIIE)<\/li>\n
- \u00a0Thibaut Germain (2020)<\/li>\n
- Randa El Mrabet-Tarmach (2020 MVA)<\/li>\n
- Mohammed Hssein (2022 MVA)<\/li>\n
- Jules Tsukahara (2022 MVA)<\/li>\n
- Ivan Conjeaud (2022 PSE)<\/li>\n
- Perceval Beja-Battais (2023 MVA)<\/li>\n
- Gwendal Debaussart (2023 Math AI)<\/li>\n
- Eloi Campagne (2023 MVA – EDF)<\/li>\n
- Gaspard Abel (2023 ENS P.S. Physics)<\/li>\n
- Louise Allain (2024 MVA)<\/li>\n
- Yutai Zhao (2025 MHPC P.S.)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n
- \n
- Master 1<\/strong>\n
- \n
- Ot\u00e1vio Leite Bastos de Nazar\u00e9 (2017 M1 ENSTA)<\/li>\n
- Marin Scalbert (2017)<\/li>\n
- Thales Loiola Raveli (2018 M1 ENSTA)<\/li>\n
- Ivan Conjeaud (2020a ENS ARIA)<\/li>\n
- Ivan Conjeaud (2021b ENS ARIA)<\/li>\n
- Mohamed El Khames (M1 ENSTA 2020)<\/li>\n
- Kais Cheikh (M1 ENSTA 2020)<\/li>\n
- Aaron MAMANN (2021)<\/li>\n
- Gaspard Abel (2021a M1 ENS P.S. Physics)<\/li>\n
- Gaspard Abel (2022b M1 ENS P.S. Physics)<\/li>\n
- Haytham Borchani (2022 M1 ENSTA Paris)<\/li>\n
- Mohamed Aymen Bouyahia (2023 M1 ENSTA Paris)<\/li>\n
- Jeanne Belly (2024 M1 ENS P.S. ARIA)<\/li>\n
- Teo Tessier (2024 M1 ENS P.S. ARIA)<\/li>\n
- Silviu-Adrian Predoi (2024 M1 ENS P.S. Physics)<\/li>\n
- Itai Zehavi (2025 M1 ENS P.S. ARIA)<\/li>\n
- Itai Zehavi (2025 M1 ENS P.S. ARIA – EDF)<\/li>\n
- Mahdi Hadj Taieb (2025 M1 ENSTA Paris)<\/li>\n
- Mohamed Benloughmari (2025 M1 ENSTA Paris)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n
- \n
- L3<\/strong> (mostly teams of two, ENS P.S. Maths)\n
- \n
- Patrick Saux and David Marchand (2014)<\/li>\n
- Pierre Abgrall and Jules Baleyte (2015)<\/li>\n
- Suzanne Schlich and Julie Tourniaire (2015)<\/li>\n
- Emile Ciuperca and Mathieu Helfter (2018)<\/li>\n
- Antoine Prouff and Antoine Bordas (2018)<\/li>\n
- Vincent Laheurte and Ferdinand Campos (2019)<\/li>\n
- Rafael Gromit and Blandine Galiay (2019)<\/li>\n
- Martin Dhaussy (2020 ENS P.S. Economics)<\/li>\n
- Baptiste Loreau and Wendong Liang (2020)<\/li>\n
- Timoth\u00e9 Chamb\u00e9ry and Alexandre Surin (2021)<\/li>\n
- Florian Ch\u00e2tel (2022)<\/li>\n
- Antonin Casel and Ilyes Belkacem (2022)<\/li>\n
- Manon Gouttefangeas and David Pieroucci (2023)<\/li>\n
- Quentin Boiret and Amer Essakine (2023)<\/li>\n
- Tokinirina Hansen and Yorick Libiot (2024)<\/li>\n
- Yann Moinard and Nidhal Sellik (2025)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/div>\n
Centre Borelli in a sentence<\/h3>
<\/div>![\"\"](\"https:\/\/i0.wp.com\/kalogeratos.com\/psite\/wp-content\/uploads\/Centre_Borelli_Logo.jpg?resize=97%2C97&ssl=1\")
<\/em><\/p>CB is a unique<\/strong> and dynamic<\/strong> environment where academic research<\/strong> is developed and challenged through real-world applications<\/strong>.<\/em><\/p><\/div>
<\/div><\/div><\/div><\/div><\/div>\nAnnouncements<\/h2>\n
Research internship subjects (Master level)<\/h3>
<\/div>![\"\"](\"https:\/\/i0.wp.com\/kalogeratos.com\/psite\/wp-content\/uploads\/1_R-YVKn5bBcpYZDr-DNDilw.jpg?resize=600%2C432&ssl=1\")
<\/p>- Curriculum learning foundation methods<\/span><\/span><\/li>
- Graph representation learning within the diffusion maps framework<\/li>
- Data clustering foundation methods<\/li>
- Graph-based statistical machine learning methods<\/li><\/ul><\/div>
<\/div><\/div><\/div>Open PhD position<\/h3>
<\/div>![\"\"](\"https:\/\/i0.wp.com\/kalogeratos.com\/psite\/wp-content\/uploads\/image-1-e1703881217768.png?resize=600%2C593&ssl=1\")
<\/p>We are actively looking to fill an open PhD position on Online change-point detection for structured multivariate time series. Read more<\/a>.<\/p><\/div>
<\/div><\/div><\/div><\/div><\/div>\nNews [bits and pieces]<\/h2>\n
- \n
- Talk@GML26:<\/strong> This year, the Geometry, Topology and Machine Mearning Workshop 2026<\/a> will be held in Paris, 18-22 May. Glad for the invitation to talk on our recent work (subject TBA).<\/li>\n
- \u03a4CSS: <\/strong>The article <\/span><\/span>Uncovering Social Network Activity Using Joint User and Topic Interaction<\/em><\/strong>, co-authored with G. Abel, J.-P. Nadal, and J. randon-Furling, has been accepted to the journal IEEE Transactions on Computational Social Systems [pdf<\/a>][code<\/a><\/span>].<\/li>\n
- Preprints:<\/strong>\n
- \n
- Dual-Criterion Curriculum Learning:
\nApplication to Temporal Data<\/em><\/strong>, co-authored with G. Abel, E. Campagne, and M. Benloughmari, 2026. [pdf<\/a>][code soon]<\/li>\n- Enhancing LIME using Neural Decision Trees<\/em><\/strong>, co-authored with M. Aymen Bouyahia, 2026. [pdf<\/a>][code<\/a><\/span>]<\/li>\n
- Enhancing Exploration in Global Optimization by Noise Injection in the Probability Measures Space<\/em><\/strong>, co-authored with G. Serr\u00e9, P. Germain, and S. Gruffaz, 2026. [pdf<\/a>]<\/li>\n
- Parametrized Power-Iteration Clustering for Directed Graphs<\/em><\/strong>, co-authored with G. Debaussart-Joniec, H. Sevi, and M. Jonckheere, 2026. [pdf<\/a>]<\/li>\n
- Cascaded Transfer: Learning Many Tasks under Budget Constraints<\/em><\/strong>, co-authored with E. Campagne, Y. Amara-Ouali, Y. Goude, and M. Mougeot, 2026. [pdf<\/a>]<\/li>\n
- Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints<\/em><\/strong>, co-authored with S. Gruffaz, G. Singer, O. Vo Van, and N. Vayatis, 2026. [pdf<\/a>]<\/li>\n
- Reducing Recurrent Competitive Epidemics via Dynamic Resource Allocation<\/em><\/strong>, co-authored with G. Abel, and S. Sarao-Mannelli, 2025. [pdf<\/a>]<\/li>\n
- Multi-view diffusion geometry using intertwined diffusion trajectories<\/em><\/strong>, co-authored with G. Debaussart-Joniec, 2025. [pdf<\/a>][code<\/a><\/span>]<\/li>\n
- Formal equivalence between global optimization consistency and random search<\/em><\/strong>, co-authored with G. Serr\u00e9 and N. Vayatis, 2025. [pdf<\/a>][Lean code<\/span><\/a>]<\/li>\n<\/ul>\n<\/li>\n
- ARCOM conf.:<\/strong> Gaspard Abel presented our work on multivariate Hawkes processes for social interactions and visualization at ARCOM’s event (co-organized with ENS P.S.). His talk had the title Analyse multi-\u00e9chelle de la diffusion d\u2019informations dans les r\u00e9seaux sociaux<\/em><\/strong> [read more<\/a>].<\/li>\n
- PhD position<\/span>:<\/strong> We are actively looking to fill an open PhD position on online change-point detection for structured multivariate time series. Read more<\/a>.<\/li>\n
- Preprint:<\/strong> the new preprint Graph Neural Networks for Electricity Load Forecasting<\/em><\/strong> consolidates two works that has been earlier presented in two ECML Workshops (2024<\/a> & 2025<\/a>). Co-authored with E. Campagne, Y. Amara-Ouali, Y. Goude, and I. Zehavi. [pdf<\/a>][code<\/a><\/span>]<\/li>\n
- Code: <\/span><\/strong><\/span>The GraphToolbox<\/em><\/strong> is a Python package designed for graph machine learning focused on time-series forecasting. It provides tools for data handling, model building, training, evaluation, and visualization. Developed as part of the work of our PhD student Eloi Campagne.<\/li>\n
- JMLR: <\/strong><\/span>The paper Collaborative likelihood-ratio estimation over graphs<\/strong><\/em>, co-authored with A. de la Concha and N. Vayatis has been accepted in the Journal of Machine Learning Research. [pdf<\/a>][code<\/a><\/span>]<\/li>\n
- Preprint:<\/strong> a new version of the working paper Generalized Dirichlet Energy and Graph Laplacians for Clustering Directed and Undirected Graphs<\/em><\/strong>, in which we present the a Generalized Spectral Clustering methodology. Except from H. Sevi and M. Jonckheere with who we initiated this project, now G. Debaussart-Joniec and M. Hacini have joined and helped with the “refurnishing” and thorough empirical validation [pdf<\/a>].<\/li>\n
- New pre-doc:<\/strong><\/span> Gabriel Singer has started a pre-doc with us and in collaboration with SNCF (in the frame of the IDAML Chair).<\/li>\n
- New intern:<\/strong><\/span>\n
- \n
- Mohamed Ben Loughmari (M1 ENSTA Paris) on advanced learning techniques for temporal point processes (Oct\u2013Dec).<\/li>\n<\/ul>\n<\/li>\n
- Pattern Recognition: <\/strong><\/span>The paper UniForCE: The unimodality forest method for clustering and estimation of the number of clusters<\/em><\/strong>, co-authored with G. Vardakas and A. Likas, has been accepted to the Pattern Recognition journal (Elsevier) and will appear soon. [pdf to be updated<\/a>][code<\/a><\/span>]<\/li>\n
- ECML 2025: <\/strong>the paper Plugging Attention Matrices into Power Grids: Towards Transparent Forecasting<\/strong><\/em>, co-authored along with E. Campagne, I. Zehavi, Y. Amara-Ouali, and Y. Goude, will appear at the ECML 2025 Workshop on Machine Learning for Sustainable Energy Systems (ML4SPS). [pdf<\/a>]<\/li>\n
- ANR oroject:<\/strong> The project SCOPED has been accepted by the ANR (the french national research agency). We are excited for the excellent potential offered by this project for exchanges and collaborations. The project is led by C\u00e9dric Richard<\/a>, Laboratoire Lagrange, Universit\u00e9 C\u00f4te d’Azur, and from Centre Borelli there will be involvement by L. Oudre, N. Vayatis, and myself.<\/li>\n
- Code: <\/span><\/strong><\/span>Check the MultiLayerNetViz<\/a> tool, which is developed in our team by Gaspard Abel, for visualization of social interaction data in a multilayer network layout.<\/li>\n
- Preprint:<\/strong> a new version of the working paper Efficient stream-based Max-Min diversification with minimal failure rate <\/strong><\/em>has been posted on arxiv [
- ECML 2025: <\/strong>the paper Plugging Attention Matrices into Power Grids: Towards Transparent Forecasting<\/strong><\/em>, co-authored along with E. Campagne, I. Zehavi, Y. Amara-Ouali, and Y. Goude, will appear at the ECML 2025 Workshop on Machine Learning for Sustainable Energy Systems (ML4SPS). [pdf<\/a>]<\/li>\n
- Enhancing LIME using Neural Decision Trees<\/em><\/strong>, co-authored with M. Aymen Bouyahia, 2026. [pdf<\/a>][code<\/a><\/span>]<\/li>\n
- \u03a4CSS: <\/strong>The article <\/span><\/span>Uncovering Social Network Activity Using Joint User and Topic Interaction<\/em><\/strong>, co-authored with G. Abel, J.-P. Nadal, and J. randon-Furling, has been accepted to the journal IEEE Transactions on Computational Social Systems [pdf<\/a>][code<\/a><\/span>].<\/li>\n
- Curriculum learning foundation methods<\/span><\/span><\/li>
- L3<\/strong> (mostly teams of two, ENS P.S. Maths)\n
- Master 1<\/strong>\n
- Master 2<\/strong>\n
- Gwendal Debaussart<\/a> (~ graph representation learning)<\/li>\n
- Long CV<\/a> (last update: 23 March 2025)<\/small>\n