Abstract

Most real systems consist of a large number of interacting, multityped components, while most contemporary researches model them as homogeneous information networks, without distinguishing different types of objects and links in the networks. Recently, more and more researchers begin to consider these interconnected, multi-typed data as heterogeneous information networks (HIN), and 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 mining 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. It will include the following aspects: (1) basic concepts in this field; (2) meta-path based data mining; (3) HIN embedding; (4) applications; (5) future work. 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.

Tutorial Materials Recent Developments of Deep HIN Analysis-Part I:Introduction
Recent Developments of Deep HIN Analysis-Part II:Metapath based DataMining
Recent Developments of Deep HIN Analysis-Part III:Heterogeneous Information Network Embedding
Recent Developments of Deep HIN Analysis-Part IV:Applications
Recent Developments of Deep HIN Analysis-Part V:Conclusion and FutureWork
Tutors

Chuan Shi, Beijing University of Posts and Telecommunications
 E-mail: shichuan@bupt.edu.cn
 Tel: +86-18910103988
 Web-page: www.shichuan.org
Philip Yu, University of Illinois at Chicago
 E-mail: psyu@uic.edu
 Tel: (312) 996-0498
 Web-page: http://www.cs.uic.edu/PSYu

Target audience, prerequisites, and benefits.

The topics of this tutorial cover main research directions of social network analysis; and the target audiences are those who are interesting in heterogeneous network mining, representation learning and analysis from both academia and industry. The expected audiences have background on data mining. It is better for them to know social network analysis.

Social network network is a mainstream direction of data mining. Moreover, heterogeneous network mining is becoming a hot topic, and it is also widely used in many applications. The participants will know the recent developments of this direction, and learn to apply them to solve real problems.

Outline of the tutorial

In this tutorial, we will give a survey on heterogeneous information network (HIN) analysis and introduce recent developments in this field. It includes the following aspects: (1) basic concepts in this field; (2) meta-path based data mining; (3) HIN embedding; (4) applications; (5) future work. 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.

The tutorial will cover the main and important work in this field. We have collected most of work in my webpage: http://www.shichuan.org/HIN_topic.html. We will select some important and representative work to present in the tutorial.

A list of the most important references that will be covered in the tutorial.

1. Yizhou Sun, Jiawei Han, Xifeng Yan, Philip S. Yu, Tianyi Wu. PathSim: Meta Path-Based Top-k Similarity Search in Heterogeneous Information Networks. VLDB Endowment, vol.4 pp. 992-1003, 2011

2. Yizhou Sun, Yintao Yu, Jiawei Han. Ranking-Based Clustering of Heterogeneous Information Networks with Star Network Schema. KDD 2009: 797-806.

3. Huang Z, Zheng Y, Cheng R, et al. Meta structure: Computing relevance in large heterogeneous information networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 1595-1604.

4. YuXiao Dong, Nitesh V. Chawla, Ananthram Swami. Metapath2vec: Scalable Representation Learning for Heterogeneous Networks. KDD 2017.

5. Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, Jie Tang. Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec. WSDM 2018.

6. Tao-yang Fu, Wang-Chien Lee, Zhen Lei. HIN2vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning. CIKM 2017.

7. Binbin Hu, Chuan Shi, Xin Zhao, Philip S. Yu. Leveraging Meta-path based Context for Top-N Recommendation with A Neural Co-Attention Model. KDD 2018

8. Chuan Shi, Xiangnan Kong, Yitong Li, Philip S. Yu, Bin Wu. HeteSim: A General Framework for Relevance Measure in Heterogeneous Networks, IEEE Transactions on Knowledge and Data Engineering, 2014.

9. Chuan Shi, Philip S. Yu. Heterogeneous Information Network Analysis and Applications. Springer. ISBN 978-3-319-56211-7. 2017.

10. Chuan Shi, Yitong Li, Jiawei Zhang, Yizhou Sun, Philip S. Yu. A survey on Heterogeneous Information Network Analysis. IEEE Transactions on Knowledge and Data Engineering, 29(1), 17-37, 2017.

11. Shaohua Fan, Junxiong Zhu, Xiaotian Han, Chuan Shi, Linmei Hu, Biyu Ma, Yongliang Li Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation. KDD2019

12. Binbin Hu, Yuan Fang, Chuan Shi. Adversarial Learning on Heterogeneous Information Networks. KDD 2019

13. Chuan Shi, Binbin Hu, Wayne Xin Zhao, Philip S. Yu. Heterogeneous Information Network Embedding for Recommendation. IEEE Transactions on Knowledge and Data Engineering, 2018.

14. Xiao Wang, Houye Ji, Chuan Shi, et al. Heterogeneous Graph Attention Network. WWW 2019.

15. Binbin Hu, Zhiqiang Zhang, Chuan Shi, Jun Zhou, Xiaolong Li, Yuan Qi. Cash-out User Detection based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism. AAAI 2019.

16. Yuanfu Lu, Chuan Shi, Linmei Hu, Zhiyuan Liu. Relation Structure-Aware Heterogeneous Information Network Embedding. AAAI 2019.