Learning graph representations with random walks: models and applications
Abstract: Machine learning on graphs is an important task with a plethora of cross-disciplinary applications, ranging from recommender systems to social network analysis and bioinformatics. The main challenge here is to find appropriate representations of the graph structure that can easily be exploited by machine learning models. As a prominent recent paradigm in graph analysis, graph representation learning (GRL) aims at finding node embeddings in a way that the structure of the network and its various properties are preserved in the lower dimensional space representations. In this talk, I will present our recent work in GRL, focusing on models that leverage random walks to capture rich structural semantics of real-world graphs. I will also discuss practical applications of GRL, including node classification, link recommendation, and data integration in bioinformatics.
Bio: Fragkiskos Malliaros (http://fragkiskos.me) is an Assistant Professor at Paris-Saclay University, CentraleSupélec and associate researcher at Inria Saclay. He also co-directs the M.Sc. Program in Data Sciences and Business Analytics (CentraleSupélec and ESSEC Business School). He was a postdoctoral researcher at UC San Diego (2016-17) and École Polytechnique (2015-16). He received his Ph.D. in Computer Science from École Polytechnique (2015) and his Diploma (2009) and M.Sc. (2011) degrees from the University of Patras, Greece. He is the recipient of the 2012 Google European Doctoral Fellowship in Graph Mining, the 2015 Thesis Prize by École Polytechnique, and best paper awards at TextGraphs-NAACL 2018 and AAAI ICWSM 2020 (honorable mention). In the past, he has been the co-chair of various data science-related workshops. He has also presented twelve invited tutorials at international conferences in the areas of graph mining and data science (e.g., ICDM, WSDM, WWW, EMNLP, EDBT). His research interests span the broad area of data science, focusing on graph mining, machine learning, and graph-based information extraction.
Also on Zoom meeting at:
MeetingID: 872 8830 4331