Abstract: A clique is a traditional model of a community in social networks. Recently there has been increasing evidence that it might not be the best, though, and more research interest has focused to community models “beyond blocks”. In this talk, we will propose one model, the hyperbolic community model, that subsumes many of the existing models. We will show the benefits of the proposed method and a case study of analysing social activity in Q&A networks. Finally, we will also present a method to find such communities. The method is based on less-known matrix concepts of (sub-)tropical matrix decomposition and rounding rank.
Professor of Data Science - School of Computing - University of Eastern Finland
Bio: Pauli Miettinen is a Professor of Data Science and the head of Algorithmic Data Analysis group at University of Eastern Finland. Before joining UEF, he was a a senior researcher at the Max-Planck Institute for Informatics, Germany. He is also an Adjunct Professor (docent) of Computer Science at the University of Helsinki, Finland, where he received his PhD in 2009. His main research interest is in Algorithmic Data Analysis. In particular, he has been working on matrix decompositions over non-standard algebras and their applications to data mining and on redescription mining. His work spans both the theory and methodology of data analysis as well as real-world applications thereof. He is an author of numerous articles published in top data mining venues, winning three best paper awards. He is an action editor of Data Mining and Knowledge Discovery journal, published by Springer Nature.