Название: Heterogeneous Graph Representation Learning and Applications
Автор: Chuan Shi, Xiao Wang, Philip S. Yu
Издательство: Springer
Серия: Artificial Intelligence: Foundations, Theory, and Algorithms
Год: 2022
Страниц: 329
Язык: английский
Формат: pdf (true), epub
Размер: 33.7 MB

Representation learning in heterogeneous graphs (HG) is intended to provide a meaningful vector representation for each node so as to facilitate downstream applications such as link prediction, personalized recommendation, node classification, etc. This task, however, is challenging not only because of the need to incorporate heterogeneous structural (graph) information consisting of multiple types of node and edge, but also the need to consider heterogeneous attributes or types of content (e.g. text or image) associated with each node. Although considerable advances have been made in homogeneous (and heterogeneous) graph embedding, attributed graph embedding and graph neural networks, few are capable of simultaneously and effectively taking into account heterogeneous structural (graph) information as well as the heterogeneous content information of each node.

Graphs and networks are ubiquitous in today’s interconnected world. Among complex network models, a specific one, called heterogeneous network (or heterogeneous graph), which models real-world systems as interactions among a massive set of multi-modal and multi-typed objects, is of particular importance because the explicit modeling of the inherent structure of complex networks facilitates powerful, in-depth network analysis. In recent years, representation learning (which is also known as embedding learning), which represents high-dimensional data with lower dimensional distributions by various Deep Learning or embedding methods, has been rapidly developed as a powerful tool for high-dimensional data analysis. Similarly, graph representation learning (also called network embedding), which learns representations of nodes/edges in a lower-dimensional space, has demonstrated its effectiveness for various graph mining and graph analysis tasks.

In this book, we provide a comprehensive survey of current developments in HG representation learning. More importantly, we present the state-of-the-art in this field, including theoretical models and real applications that have been showcased at the top conferences and journals, such as TKDE, KDD, WWW, IJCAI and AAAI. The book has two major objectives: (1) to provide researchers with an understanding of the fundamental issues and a good point of departure for working in this rapidly expanding field, and (2) to present the latest research on applying heterogeneous graphs to model real systems and learning structural features of interaction systems. To the best of our knowledge, it is the first book to summarize the latest developments and present cutting-edge research on heterogeneous graph representation learning. To gain the most from it, readers should have a basic grasp of Computer Science, Data Mining and Machine Learning.