Michalis Vazirgiannis
     

We have available PhD and post doctoral opportunities in our team! More info here.


    
Michalis Vazirgiannis

Dr. Vazirgiannis is a Professor at LIX, Ecole Polytechnique in France and leads the Data Science and Mining group (DaSciM).

He holds a degree in Physics and a PhD in Informatics from Athens University(Greece) and a Master degree in AI from Heriot Watt University,Edinburgh (UK). He has conducted research in Frauhofer, Max Planck MPI (Germany), in INRIA/FUTURS (Paris). He has been teaching in AUEB (Greece), Ecole Polytechnique, Telecom-Paristech, ENS (France), Tsinghua, Jiaotong Shanghai (China) and in Deusto University (Spain). His current research interests are on machine/deep learning and combinatorial methods for Graph analysis (including community detection, graph clustering, node embeddings and influence maximization), Text mining (including Graph of Words, word embeddings with applications to web advertising and marketing, event detection and summarization). He has active cooperation with industrial partners in the area of analytics and machine learning for large scale data repositories in different application domains (including recommendations, meeting summarizatiom, influence metrics for scientific and social networks, predictive maintenance and others). He has supervised fifteen completed PhD theses. He has published three books and more than a 160 papers in international refereed journals and conferences. He has organized large scale conferences in the area of Data Mining and Machine Learning (such as ECML/PKDD) while he participates in the senior PCs of AI and ML conferences – such as AAAI and IJCAI, He has received the ERCIM and the Marie Curie EU fellowships, the Tencent “Rhino-Bird International Academic Expert Award” in 2017 and since 2015 he leads the AXA Data Science chair.

The DaSciM team members have supervised fifteen completed Ph.D. theses and published chapters in books and encyclopedias, two international books and more than a 250 papers in international refereed journals and conferences. Also we have co-authored three patents and attracted significant R&D funding including national and international governmental/industrial sources. Members of our team have received the ERCIM, Marie Curie, and Google fellowships. Our team has co-organized the ECML PKDD 2011 conference in Athens, ECML/PKDD 2017 and participates in the senior organization of different AI and Data mining related events (AAAI, IJCAI).

Moreover our group has a long experience in real-world R&D projects in the area of Large Scale Data/Text/time series Mining. Currently we maintain collaborations with industrial partners (including AIRBUS, Google, BNP, Tencent, Tradelab) working on machine learning projects.

Professor Vazirgiannis lead the X/AXA Data Science Chair (2015-2018) and currently leads the ANR-HELAS chair on Deep Learning for heterogeneous data (graphs,text).


What's new

  • June 2020: Check Prof. M. Vazirgiannis article in Annals des Mines offering a popularised presentation of AI challenges for the future. See more here.
  • July 2020: Prof. Vazirgiannis gave a keynote talk @WIMS (International Conference on Web Intelligence, Mining and Semantics) on July 1, 2020. See more details here.
  • June 2020: Prof. Vazirgiannis gave a keynote talk @DL4KG (Deep Learning for Knowledge Graphs) on June 2nd, 2020. See more details here.

Latest publications

  • S Limnios, G Dasoulas, DM Thilikos, M Vazirgiannis, Hcore-Init: Neural Network Initialization based on Graph Degeneracy , arXiv preprint arXiv:2004.07636, 2020
  • G Shang, AJP Tixier, M Vazirgiannis, JP Lorré, Speaker-change Aware CRF for Dialogue Act Classification , arXiv preprint arXiv:2004.02913, 2020
  • C Xypolopoulos, AJP Tixier, M Vazirgiannis, Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings , arXiv preprint arXiv:2003.10224, 2020
  • C Wu, G Nikolentzos, M Vazirgiannis, EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs , arXiv preprint arXiv:2003.00842, 2020
  • G Dasoulas, G Nikolentzos, K Scaman, A Virmaux, M Vazirgiannis, Ego-based Entropy Measures for Structural Representations , arXiv preprint arXiv:2003.00553, 2020
  • G Salha, R Hennequin, JB Remy, M Moussallam, M Vazirgiannis, FastGAE: Fast, Scalable and Effective Graph Autoencoders with Stochastic Subgraph Decoding , arXiv preprint arXiv:2002.01910, 2020
  • G Salha, R Hennequin, M Vazirgiannis, Simple and effective graph autoencoders with one-hop linear models , arXiv preprint arXiv:2001.07614, 2020
  • FD Malliaros, C Giatsidis, AN Papadopoulos, M Vazirgiannis, The core decomposition of networks: Theory, algorithms and applications , The VLDB Journal 29 (1), 2020
  • M Lioudakis, S Outsios, M Vazirgiannis, An Ensemble Method for Producing Word Representations for the Greek Language , arXiv preprint arXiv:1912.04965, 2019
  • C Wu, G Nikolentzos, M Vazirgiannis, Matching Node Embeddings Using Valid Assignment Kernels , International Conference on Complex Networks and Their Applications, 2019
  • G Panagopoulos, C Xypolopoulos, K Skianis, C Giatsidis, J Tang, ..., Scientometrics for Success and Influence in the Microsoft Academic Graph , International Conference on Complex Networks and Their Applications, 2019
  • S Khalife, J Read, M Vazirgiannis, Empirical Analysis of a Global Capital-Ownership Network , International Conference on Complex Networks and Their Applications, 2019
  • J Casas-Roma, J Salas, FD Malliaros, M Vazirgiannis, k-Degree anonymity on directed networks , Knowledge and Information Systems 63 (1), 2019
  • M Vazirgiannis, G Nikolentzos, G Siglidis, Machine Learning on Graphs with Kernels , Proceedings of the 28th ACM International Conference on Information and …, 2019
  • G Salha, S Limnios, R Hennequin, VA Tran, M Vazirgiannis, Gravity-inspired graph autoencoders for directed link prediction , Proceedings of the 28th ACM International Conference on Information and …, 2019
  • D Ustalov, S Somasundaran, P Jansen, G Glavaš, M Riedl, M Surdeanu, ..., Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13) , Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural …, 2019
  • S Khalife, M Vazirgiannis, Scalable graph-based method for individual named entity identification , Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural …, 2019
  • G Nikolentzos, M Vazirgiannis, Learning Structural Node Representations using Graph Kernels , IEEE Transactions on Knowledge and Data Engineering, 2019
  • G Salha, R Hennequin, M Vazirgiannis, Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks , arXiv preprint arXiv:1910.00942, 2019
  • AJP Tixier, MEG Rossi, FD Malliaros, J Read, M Vazirgiannis, Perturb and combine to identify influential spreaders in real-world networks , Proceedings of the 2019 IEEE/ACM International Conference on Advances in …, 2019
  • G Nikolentzos, AJP Tixier, M Vazirgiannis, Message Passing Attention Networks for Document Understanding , arXiv preprint arXiv:1908.06267, 2019
  • G Nikolentzos, M Vazirgiannis, Revisiting the Graph Isomorphism Problem with Semidefinite Programming , arXiv preprint arXiv:1908.06320, 2019
  • JB Remy, AJP Tixier, M Vazirgiannis, Bidirectional Context-Aware Hierarchical Attention Network for Document Understanding , arXiv preprint arXiv:1908.06006, 2019
  • J Read, N Tziortziotis, M Vazirgiannis, Error-space representations for multi-dimensional data streams with temporal dependence , Pattern Analysis and Applications 22 (3), 2019
  • G Nikolentzos, G Dasoulas, M Vazirgiannis, k-hop Graph Neural Networks , arXiv preprint arXiv:1907.06051, 2019
  • C Giatsidis, G Nikolentzos, C Zhang, J Tang, M Vazirgiannis, Rooted citation graphs density metrics for research papers influence evaluation , Journal of Informetrics 13 (2), 2019
  • G Nikolentzos, G Siglidis, M Vazirgiannis, Graph kernels: A survey , arXiv preprint arXiv:1904.12218, 2019
  • G Shang, AJP Tixier, M Vazirgiannis, JP Lorré, Energy-based self-attentive learning of abstractive communities for spoken language understanding , arXiv preprint arXiv:1904.09491, 2019
  • G Panagopoulos, FD Malliaros, M Vazirgiannis, Multi-task Learning for Influence Estimation and Maximization , arXiv preprint arXiv:1904.08804, 2019
  • S Outsios, C Karatsalos, K Skianis, M Vazirgiannis, Evaluation of Greek Word Embeddings , arXiv preprint arXiv:1904.04032, 2019
  • N Tziortziotis, C Dimitrakakis, M Vazirgiannis, Randomised bayesian least-squares policy iteration , arXiv preprint arXiv:1904.03535, 2019
  • K Skianis, G Nikolentzos, S Limnios, M Vazirgiannis, Rep the Set: Neural Networks for Learning Set Representations , arXiv preprint arXiv:1904.01962, 2019
  • G Salha, R Hennequin, VA Tran, M Vazirgiannis, A degeneracy framework for scalable graph autoencoders , arXiv preprint arXiv:1902.08813, 2019