Title: Machine Learning for Graphs - Kernels and and node embeddings
Speaker:  Professor Michalis Vazirgiannis, Ecole Polytechnique, Institute Polytechnique de Paris
Date:  Wednesday, May 4, 2022 at 16.00

The speech will be in English.
             Zoom link:  https://us02web.zoom.us/j/87239220426

Abstract: Graphs are becoming a dominant structure in current information management with many domains involved, including social networks, chemistry, biology, NLP etc. Then machine learning tasks involving graphs need valid similarity metrics that in the case of graphs pose significant challenges going beyond the simple vector based similarities.  In our group we have devoted significant efforts on the topic of graph similarity as cornerstone element of machine learning for graphs mostly in supervised tasks. We will present some cases of kernels showing how graph kernels can be exploited in diverse tasks. Also we will present briefly basic deep learning based methods for node embeddings towards graph classification. Finally we will present the Grakel  library, developed in our group,  that unifies several graph kernels into a common framework, written in Python compatible with scikit-learn.

Bio: Dr. Vazirgiannis is a Distinguished Professor at the department of Informatics,  Ecole Polytechnique, Institute Polytechnique de Paris, in France. He has conducted research in  Frauenhofer and Max Planck-MPI (Germany), in INRIA/FUTURS (Paris). He has been a 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 deep and machine learning for Graph analysis (including community detection, graph classification, clustering and embeddings, influence maximization), Text mining including Graph of Words, deep learning for word embeddings with applications to web advertising and marketing, event detection and summarization. He has active cooperation with industrial partners in the area of data analytics and machine learning for large scale data repositories in different application domains. He has supervised twenty eight completed PhD theses. He has published three books and more than a 200 papers in international refereed journals and conferences and received best paper awards in ACM CIKM2013 and IJCAI2018. 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 PC of AI and ML conferences – such as AAAI and IJCAI. He has received the ERCIM and the Marie Curie EU fellowships, the Rhino-Bird International Academic Expert Award by Tencent and between 2015 and 2018 he lead the AXA Data Science chair. Currently he leads the ANR-HELAS chair on "Deep Learning for Unstructured and graph data".