Representation Learning on Networks

Network representation learning offers a revolutionary paradigm for mining and learning with network data. In this tutorial, we will give a systematic introduction for representation learning on networks. We will start the tutorial with industry examples from Alibaba, AMiner, Microsoft Academic, WeChat, and XueTangX to explain how network analysis and graph mining on the Web are benefiting from representation learning. Then we will comprehensively introduce both the history and recent advances on network representation learning, such as network embedding and graph neural networks. Uniquely, this tutorial aims to provide the audience with the underlying theories in network representation learning, as well as our experience in translating this line of research into real-world applications on the Web. Finally, we will release public datasets and benchmarks for open and reproducible network representation learning research. 

Part 1 Introduction--History of social & information network analysis [slides]

Part 2 Network Embeddings [slides]

• 2.1 Conventional network analysis
•       Node classification
•       Social tie & link prediction
• 2.2 Node embeddings
•       Embedding models
•       Theoretical understanding
•       Large-scale embedding

Part 3 Graph Neural Networks [slides]

• 3.1 GNNs Fundamentals
•       Graph Convolution
•       Graph GAN
•       Dynamic Representation
•       Heterogeneous Representation
• 3.2 Large-scale applications
•       Knowledge graph linking
•       Recommendation in E-commerce
•       Online-to-offline recommendations
•       Social influence in gaming

Part 4 Conclusion [slides]

• 4.1 Summary
• 4.2 Open Network Embedding Data

1. Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Chi Wang, Kuansan Wang, and Jie Tang. NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization. In Proceedings of the Web Conference 2019 (WWW'19). [PDF] [data & code]
2. Fanjin Zhang, Xiao Liu, Jie Tang, Yuxiao Dong, Peiran Yao, Jie Zhang, Xiaotao Gu, Yan Wang, Bin Shao, Rui Li and Kuansan Wang. OAG: Toward Linking Large-scale Heterogeneous Entity Graphs. In Proceedings of the Twenty-Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'19).
3. Xichen Ding, Jie Tang, Tracy Liu, Cheng Xu, Yaping Zhang, Feng Shi, Qixia Jiang and Dan Shen. Infer Implicit Contexts in Real-time Online-to-Offline Recommendation. In Proceedings of the Twenty-Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'19).
4. Yukuo Cen, Xu Zou, Jianwei Zhang, Hongxia Yang, Jingren Zhou and Jie Tang. Representation Learning for Attributed Multiplex Heterogeneous Network. In Proceedings of the Twenty-Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'19).
5. Qibin Chen, Junyang Lin, Yichang Zhang, Hongxia Yang, Jingren Zhou and Jie Tang. Towards Knowledge-Based Personalized Product Description Generation in E-commerce. In Proceedings of the Twenty-Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'19).
6. Zhengxiao Du, Xiaowei Wang, Hongxia Yang, Jingren Zhou and Jie Tang. Sequential Scenario-Specific Meta Learner for Online Recommendation. In Proceedings of the Twenty-Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'19).
7. Yu Han, Jie Tang, and Qian Chen. Network Embedding under Partial Monitoring for Evolving Networks. In Proceedings of the 28th International Joint Conference on Artificial Intelligence(IJCAI'19).
8. Jie Zhang, Yuxiao Dong, Yan Wang, Jie Tang, and Ming Ding. ProNE: Fast and Scalable Network Representation Learning. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI'19).
9. Yifeng Zhao, Xiangwei Wang, Hongxia Yang, Le Song, and Jie Tang. Large Scale Evolving Graphs with Burst Detection. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI'19).
10. Jiezhong Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, and Jie Tang. DeepInf: Social Influence Prediction with Deep Learning. In Proceedings of the Twenty-Forth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'18). [PDF] [poster] [data & code] [video]
11. Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, and Jie Tang. Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining (WSDM'18). [PDF] [Slides] [code]

Jie Tang is a Full Professor and the Associate Chair of the Department of Computer Science and Technology at Tsinghua University. His interests include data mining, social networks, knowledge graph, machine learning, and artificial intelligence. He has been visiting scholar at Cornell University, Hong Kong University of Science and Technology, and Southampton University. He has published more than 300 journal/conference papers and holds 20 patents. His papers have been cited by more than 12,000 times. He served as PC Co-Chair of CIKM’16, WSDM’15, Associate General Chair of KDD’18, and Acting Editor-in-Chief of ACM TKDD, Editors of IEEE TKDE/TBD and ACM TIST. He leads the project AMiner.org for academic social network analysis and mining, which has attracted more than 10 million independent IP accesses from 220 countries/regions in the world. He was honored with the UK Royal Society-Newton Advanced Fellowship Award, CCF Young Scientist Award, NSFC for Distinguished Young Scholar, and KDD’18 Service Award.

Yuxiao Dong is a Senior Applied Scientist at Microsoft Research, Redmond. He received his Ph.D. from University of Notre Dame and has been a visiting scholar at Tsinghua University, U.S. Army Research Lab, and AMiner.org. His research focuses on data mining, network science, and computational social science, with an emphasis on applying computational models to addressing problems in large-scale networked systems, such as the Microsoft Academic Graph (MAG), mobile communication, and online social media. His work has been mainly published in KDD and interdisciplinary journals, winning four best paper awards/nominations as well as the 2017 ACM SIGKDD Doctoral Dissertation Award Honorable Mention.