Welcome to my personal web-page. I am Argyris Kalogeratos (Αργύρης Καλογεράτος), I come from Patras, Greece. My background is on Computer Science and I have a PhD on Machine Learning (2013).
Click for short bioArgyris Kalogeratos holds a PhD in Computer Science (2013) from the University of Ioannina, Greece, on Machine Learning and Information Technologies, under the supervision of Prof. Aristidis Likas. His expertise ranges from Machine Learning and Artificial Intelligence, to Complex Networks and Decision & Control. Currently, A.K. is a permanent researcher at the Borelli Research Center, ENS Paris-Saclay, and member of the Machine Learning and Massive Data Analysis group (MLMDA). He is the primary investigator of the Machine Learning on Graphs and Complex Systems research theme. His research work has been published in journals such as IEEE Transactions on Network Science and Engineering, Springer’s Knowledge and Information Systems, Elsevier’s Data and Knowledge Engineering, as well as conferences such as NeurIPS, ICML, AAAI, AISTATS, INFOCOM, CDC, and others. Being affiliated with the Industrial Data Analytics and Machine Learning Chair (IdAML) of ENS Paris-Saclay, he has been involved in several synergistic projects among Academia and Industry for problems related to multimedia mining, social network analysis and mining, computational epidemiology, marketing, transportation, communication systems, and bioinformatics.
Currently
Position: I am a permanent researcher at the Centre Giovanni Borelli (ex Centre de Mathématiques et de Leurs Applications – CMLA), Ecole Normale Supérieure Paris-Saclay (ENS Paris-Saclay), University Paris-Saclay, France, and member of the Machine Learning and Massive Data Analysis (MLMDA) research group (head: Nicolas Vayatis).
Research focus: Coordinator of the ML on Graphs research theme.
Research initiatives: I participate to the research activities of the ML Industrial Big Data Chair (C.Borelli team: Charles Truong, Harry Sevi, Argyris Kalogeratos, Mathilde Mougeot, Nicolas Vayatis — past: Julien Audiffren). Among our industrial partners, there are ATOS – Wordline, SNCF, CEA, Michelin, Bertin Tech, and Banque de France.
Past funding: My research position at CMLA has been funded in the past by the MORANE project (in collaboration with SNCF railway company) and the SODATECH project (funded by the French state) for which I was the research coordinator and responsible for CMLA’s part. See more details at the “Projects” section.
Centre Borelli in a sentence
CB is a unique and dynamic environment where the academic research is developed while being challenged in real practical and industrial applications.
Announcements
Post-doc fellowship on Graph Machine Learning
FMJH call for post-doc funding 2023. Check our subject proposal entitled Graph operator pursuit for efficient graph machine learning.Applications are due to the 1st of December 2022.
Opportunities for research internships
Here are some of the internship subjects offered by the ML team (MLMDA) of Center Borelli, for students of the MVA Masters program, but not limited to that. [link]
News
- New interns:
- Perceval Beja-Battais (M2 MVA, Apr – Oct) will work on learning theory.
- Gaëtan Serré (M2 MVA, Apr – Oct) will work on global optimization.
- Gwendal Debaussart (M2 MVA, Apr – Oct) will work on statistical machine learning.
- Eloi Campagne (M2 MVA, Apr – Oct) will work on time-series analysis and prediction (colab. with EDF).
- Gaspard Abel (M2 ENS PS Physics) on information diffusion, co-supervision with Jean-Pierre Nadal.
- Mohamed Aymen Bouyahia (M1 ENSTA Paris, May – August) will work on interpretable ML.
- Abdeljalil Zoubir (UM6P PhD visiting as an intern from Morocco, Apr – July) on graph neural networks with application to chemical compounds.
- Manon Gouttefangeas and David Pieroucci (L3 ENS Maths, Apr – Jun) on paired sample hypothesis testing.
- Quentin Boiret and Amer Essakine (L3 ENS Maths, Apr – Jun) on graph neural networks for time series.
- TechReport – The new preprint Online Centralized Non-parametric Change-point Detection via Graph-based Likelihood-ratio Estimation, co-authored with A. de la Concha and N. Vayatis, can be found at [pdf].
- Round table – I will be part of the 4-person panel of the Alumni Event organized by the Dept. Computer Science and Engineering of University of Ioannina on 9 Dec 2022 [blog post][poster].
- Workshop – The work Collaborative likelihood-ratio estimation over graphs [paper][slides][poster] will be presented by Alejandro de la Concha in NeurIPS@Paris 2022 [program] on 23 Nov.
- The new preprint DeGroot-based opinion formation under a global steering mechanism, co-authored with I. Conjeaud and P. Lorenz-Spreen, can be found at [pdf].
- Post-doc call – The Foundation FMJH has announced the call for post-doc fellowships. Check our subject proposal entitled Graph operator pursuit for efficient graph machine learning. Applications are due to the 1st of December. Contact me for more details.
- TechReport – The new preprint DeGroot-based opinion formation under a global steering mechanism, co-authored with I. Conjeaud and P. Lorenz-Spreen, can be found at [pdf].
- TechReport – The new preprint Clustering for directed graphs using parametrized random walk diffusion kernels, co-authored with H. Sevi and M. Jonckeere, can be found at [pdf].
- Workshop – The Paris-Saclay Change-Point workshop has just be announced. It is organized by members of our team, and it’s going to be held on Monday-Tuesday 16-17 January 2023 at ENS Paris-Saclay.
- ICANN2022 – The paper To tree or not to tree? Assessing the impact of smoothing the decision boundaries, co-authored with A. Merida and M. Mougeot, will appear in the Int. Conf. on Artificial Neural Networks (ICANN 2022) [pdf].
- FMJH funding – Great news to share: Harry Sevi will be funded for a 2-years post-doctoral fellowship by the Foundation for Mathematics Jacque Hadamard (FMJH) to work with me and the MLMDA team on the project “Using the graph structure to survive in high-dimensions: Graph arrangements, walks, and embeddings“.
- TechReport – The new preprint Collaborative likelihood-ratio estimation over graphs, co-authored with A. de la Concha, and N. Vayatis, can be found at [pdf].
- Conf. Talk – Our PhD student Anthea Merida will present orally her work on “Data inspection via challenging decision boundaries’ rigidity” at the Int. Conf. of Computational Statistics – COMPSTAT 2022.
- New interns:
- Mohammed Hssein (M2 MVA, May-Oct) will work on Federated Learning.
- Jules Tsukahara (M2 MVA, May-Oct) will work on graph representation learning.
- Florian Châtel (L3 Maths, ENS Paris-Saclay, Apr – Jun) will work on interpretable ML.
- Antonin Casel and Ilyes Belkacem (L3 Maths, ENS Paris-Saclay, Apr – Jun) will work on unsupervised learning on graphs.
- Ivan Conjeaud (M2 PSE, Jan – Jun) will work on a game theoretic problem on graphs.
- Gaspard Abel (M1 Economics, ENS Paris-Saclay, Feb – July) will work on competitive diffusion processes.
- Haytham Borchani (M1 ENSTA Paris, May – August) will work on interpretable ML.
- AI Cup – Last days for registering to the Franco-Bavarian AI Cup that we enthousiastically co-organize with University of Passau, Bavaria, Germany.
- Workshop poster – Harry Sevi presented our joint work with a poster at the Workshop on Recent Advancements on Graph Machine Learning of Sorbonne University.
- TechReport – A new preprint Generalized Spectral Clustering for Directed and Undirected Graphs, co-authored with H. Sevi and M. Jonckeere can be found at [arxiv page].
- TechReport – The preprint Online non-parametric change-point detection for heterogeneous data streams observed over graph nodes, co-authored with A. de la Concha and Nicolas Vayatis can be found at [arxiv page].
- New intern – Gaspard Abel (M1 Economics, ENS Paris-Saclay) will work on competition in epidemic systems.
- JMLR – The aricle “Learning Laplacian Matrix from Graph Signals with Sparse Spectral Representation“, co-authored by P. Humbert, B. Le Bars, L. Oudre, A. Kalogeratos, and N. Vayatis, has been accepted to the Journal of Machine Learning Research (JMLR), 2021. The paper comes with a python package that implements the proposed method. [pdf][bib][code]