Hi, bonjour, yeia

Welcome to my personal web-page related to my scientific interests. I am Argyris Kalogeratos (Αργύρης Καλογεράτος); well, the guy in the photo. I come from Patras, Greece, where I spent the first 18 years of my life. Later, I moved to Ioannina to study Computer Science.

I received my PhD on the field of Machine Learning from the Dept. of Computer Science, University of Ioannina, Greece (2013). The title of my research thesis was “Knowledge Extraction Methods from Document Collections” [page].

Currently

Since September 2013, I am a member of the Machine Learning and Massive Data Analysis (MLMDA) research group directed by Prof. Nicolas Vayatis at the Centre de Mathématiques et de Leurs Applications (CMLA), Ecole Normale Supérieure de Cachan (ENS Cachan – Paris Saclay, France).

My research position is funded by the MORANE project funded by the SNCF railway company for the diffusion process analysis and the development of machine learning methodologies for application on transportation networks. My role in the project is to be the primary research coordinator and responsible for the side of CMLA.

Previously, I was funded by the SODATECH project (see details in the Projects section).

News

  • Technical report – A new paper was released as Technical Report. Its title is “A Spectral Method for Activity Shaping in Continuous-Time Information Cascades” and it is co-authored with K. Scaman, L. Corinzia, and N. Vayatis. [pdf][arXiv link] Abstract

    The Information Cascades Model captures dynamical properties of user activity in a social network. In this work, we develop a novel framework for activity shaping under the Continuous-Time Information Cascades Model which allows the administrator for local control actions by allocating targeted resources that can alter the spread of the process. Our framework employs the optimization of the spectral radius of the Hazard matrix, a quantity that has been shown to drive the maximum influence in a network, while enjoying a simple convex relaxation when used to minimize the influence of the cascade. In addition, use-cases such as quarantine and node immunization are discussed to highlight the generality of the proposed activity shaping framework. Finally, we present the NetShape influence minimization method which is compared favorably to baseline and state-of-the-art approaches through simulations on real social networks.

  • New PhD student – Mathilde Fekom, previously an internship Master student at CMLA, will continue with us to the PhD adventure (starting Sep. 2017), after obtaining a highly competitive scholarship from Université Paris Saclay.
  • New students – We welcome three new students in the ML on Networks theme of MLMDA group, Mathilde Fekom (MSc thesis), Matteo Neri (MSc thesis), and Marin Scalbert (MSc internship), that are going to be with us at CMLA this semester.
  • Invited Talk – A two-hours seminar talk on “Epidemics, Competition and Resource Management” was given in Paris at a Working Group on Machine Learning and Big Data of the French Ministry of Social Affairs and Health (organizer: Magali Beffy). The group is formed by scientists and researchers working on various organizations/institutions (Ministry of Health, INSEE,  IRDES, Dauphine) – 25/1/2017.
  • MECO 2017 – Part of the ongoing work on behavioral epidemics and dynamic control done with Stefano Sarao, Kevin Scaman, and Nicolas Vayatis is going to be presented in a poster format by Stefano at the 42nd Middle European Cooperation in Statistical Physics (MECO), Feb 2017, Lyon, France.
  • ΑΑΑΙ 2017 Multivariate Hawkes Processes for Large-scale Inference“, co-authored with Rémi Lemonnier and Kevin Scaman, will appear in the 31st AAAI Conference on Artificial Intelligence (AAAI-17), San Francisco, CA, US. [638 papers accepted / 2,590 submissions : 24.63% rate] – [pdf][supplementary][poster].
    Abstract

    In this paper, we present a framework for fitting multivariate Hawkes processes for large-scale problems both in the number of events in the observed history n and the number of event types d (i.e. dimensions). The proposed Low-Rank Hawkes Process (SLRHP) framework introduces a low-rank approximation of the kernel matrix that allows to perform the nonparametric learning of the d^2 triggering kernels using at most O(ndr^2) operations, where r is the rank of the approximation (r << d, n). This comes as a major improvement to the existing state-of-the-art inference algorithms that are in O(nd^2). Furthermore, the low-rank approximation allows SLRHP to learn representative patterns of interaction between event types, which is usually for the analysis of complex processes in real-world networks.

  • Jury member in PhD defense Kevin Scaman successfully defended in October his PhD thesis at CMLA, ENS Cachan. I am glad that I have been co-supervisor and collaborator to Kevin for three years, and finally a jury member in his defense.
  • MORANE project  The project that I will be primarily been involved in the next year has been launched on Sep. 2016 and is in collaboration with SNCF, the French National Railway Company (read more).
  • CCS 2016 – Part of our work with Stefano Sarao, Kevin Scaman, and Nicolas Vayatis, appeared at the Conference on Complex Systems 2016 at Amsterdam as a full oral presentation entitled “Dynamic control of social diffusion using extensions of the SIS model” (on a working paper).
  • PC Member 2nd International Workshop on “Data Science for Social Media and Risk“, part of IEEE ICDM 2016.
  • Journal paper – “Suppressing Epidemics in Networks using Priority-Planning”, co-authored with K. Scaman, and N. Vayatis, published in IEEE Transactions on Network Science and Engineering (TNSE) [pdf][bib]. Abstract

    In this paper, we analyze a large class of dynamic resource allocation (DRA) strategies, named priority planning, that aim to suppress SIS epidemics taking place in a network. This is performed by distributing treatments of limited efficiency to its infected nodes, according to a priority-order precomputed offline. Under this perspective, an efficient DRA strategy for a given network can be designed by learning a proper linear arrangement of its nodes. In our theoretical analysis, we derive upper and lower bounds for the extinction time of the diffusion process that reveal the role of the maxcut of the considered linear arrangement. Accordingly, we highlight that the cutwidth, which is the minimum maxcut of all possible linear arrangements for a network, is a fundamental network property that determines the resource budget required to suppress the epidemic under priority planning. Finally, by making direct use of our theoretical results, we propose a novel and efficient DRA strategy, called maxcut minimization (MCM), which outperforms other competing strategies in our simulations, while offering desirable robustness under various noise profiles.

  • Invited Talk – Dynamic suppression of epidemics on networks“, at the  Complex Networks research group of LIP6, Paris 6 (Jussieu), France, 13/6/2016.
  • Invited Talk – Epidemics in the new socio-economic era: challenges and applications“, at the Department of Computer Science and Engineering, University of Ioannina, Greece, 25/5/2016.
  • Invited Talk – Suppressing epidemics on arbitrary networks using treatment resources of limited efficiency“, at INRA Research Center at Jouy-en-Josas, Paris area, 4/3/2016.
  • TechReport A technical report under the title “Multivariate Hawkes Processes for Large-Scale Inference“, co-authored with R. Lemonnier and K. Scaman was released, Feb 26, 2016. [arXiv link][pdf][bib].
    Abstract

    In this paper, we present a framework for fitting multivariate Hawkes processes for large-scale problems both in the number of events in the observed history n and the number of event types d (i.e. dimensions). The proposed Low-Rank Hawkes Process (LRHP) framework introduces a low-rank approximation of the kernel matrix that allows to perform the nonparametric learning of the d^2 triggering kernels using at most O(ndr^2) operations, where r is the rank of the approximation (r << d, n). This comes as a major improvement to the existing state-of-the-art inference algorithms that are in O(nd^2). Furthermore, the low-rank approximation allows LRHP to learn representative patterns of interaction between event types, which may be valuable for the analysis of such complex processes in real world datasets. The efficiency and scalability of our approach is illustrated with numerical experiments on simulated as well as real datasets.

  • SETN 2016 – Accepted paper “Improving Text Stream Clustering using Term Burstiness and Co-burstiness“, co-authored with P. Zagorisios and A. Likas, at the Hellenic Conference of Artificial Intelligence (SETN), May 18-20, 2016. [pdf][slides][bib]. Abstract

    In text streams, documents appear over time and their timestamps can be used to improve typical approaches for text representation and clustering. A way to exploit temporal information is through the detection of bursty terms in such streams, i.e. terms that appear in many documents during short time period. Research efforts so far have shown that utilizing the burst information in the text representation can improve the performance of text clustering algorithms. However, most attempts take into account the bursty terms individually, without investigating the relation between them.

    In this work, we take advantage of the fact that most of the important documents of a topic are published during the period in which the `main’ topic terms are bursty. Therefore, we focus on both term burstiness and co-burstiness by determining groups of terms that are simultaneously bursty at a time period and also co-occurring in the same documents. Next, the documents that contain co-bursty terms from those groups, are considered as important for the respective topics and are used to construct robust synthetic prototypes following an agglomerative process. These prototypes are finally used to initialize in a deterministic fashion the spherical k-means clustering algorithm. Experimental results validate empirically the quality of the solutions provided by the proposed approach which seems to efficiently overcome the initialization problem of spherical k-means.

See all news…


Curriculum Vitae (updated on June 2017)