Recent Developments of Deep Heterogeneous Information Network Analysis

Abstract

Recently, there is a surge of research on employing Heterogeneous Information Networks (HIN) to model complex interaction system, where networks compose of different types of nodes or links, since HIN contains richer structure and semantic information. Many researches develop structural analysis approaches by leveraging the rich semantic meaning of structural types of objects and links in the networks. Furthermore, recent advancement on deep learning and network embedding poses new opportunities and challenges to mine HIN, and heterogeneous network embedding, even heterogeneous graph neural network, is becoming a hot topic. In this tutorial, we will give a survey on recent developments of heterogeneous information network analysis, especially on newly emerging heterogeneous network embedding. This tutorial shall help researchers and practitioners to share new techniques for identifying and analyzing relationships in networks that integrate multiple types or sources of information.