Graph Representation Learning & its Applications


raph structured data are ubiquitous nowadays in a variety of disciplines and domains ranging from computer science, social science, economics, medicine, to bioinformatics. Examples include social networks, knowledge graph, e-commerce networks, protein-protein interaction graphs, and molecular structures. Recently, representation learning for graphs has attracted considerable attention from researchers and communities, and led to state-of-the-art results in numerous tasks including molecule classification, new drug discovery, recommender systems, etc. This workshop aims to provide a forum for industry and academia to discuss the latest progress on graph representation learning and their applications in different fields. We expect novel research works that address various aspects of graph representation learning, including learning representations of entire graph, knowledge graph embedding, graph neural networks, applications in information network analysis, natural language understanding, recommender systems, drug discovery, and so on.

The theme of this workshop is to explore graph representation learning methods or technologies for information and knowledge management. In particular, topics of interest include but are not limited to:

Unsupervised node representation learning
Learning representations of entire graphs
Graph neural networks
Graph generation
Heterogeneous graph embedding
Knowledge graph embedding
Graph alignment
Graph matching
Dynamic graph representation

Graph representation learning for relational reasoning
Graph anomaly detection
Applications in recommender systems
Applications in information network analysis
Applications in natural language understanding
Applications in traffic predictions
Applications in social network analysis
Applications in drug discovery
Other applications


Time Event
14:00-14:05 Welcome
14:05-14:45 Keynote Speaker: Xing Xie (Microsoft Research Asia)
Title: Knowledge Enhanced Recommendation Systems
14:45-15:30 Paper Presentations:
  • Node-Feature Convolution for Graph Convolutional Networks;
  • UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks;
  • NISER: Normalized Item and Session Representations with Graph Neural Networks.
  • 15:30-16:00 Break
    16:00-16:20 Paper Presentations:
  • A Unified Network Embedding Algorithm for Multi-type Similarity Measures;
  • Student Performance Prediction based on Multi-View Network Embedding.
  • 16:20-17:00 Keynote Speaker: Shirui Pan (Monash University)
    Title: Towards Dynamic and Efficient Graph Neural Networks


    Xing Xie

    Microsoft Research Asia

    Title of Keynote: Knowledge Enhanced Recommendation Systems
    Abstract: The explosive growth of online contents and services has provided overwhelming choices for users. Recommender Systems intend to address the information explosion by finding a small set of items for users to meet their personalized interests. In most recommendation scenarios, items may contain rich knowledge information. The network structure that captures such knowledge is referred to as the knowledge graph. The knowledge graph greatly expands the amount of information of each item and strengthens the connection between them, providing abundant reference values for a recommendation engine, which leads to additional diversity and explainability of the recommendation result. In this talk, I will introduce opportunities and challenges, as well as our recent research works in this area.
    Biography: Xing Xie is currently a senior principal research manager at Microsoft Research Asia, and a guest Ph.D. advisor at the University of Science and Technology of China. He received his B.S. and Ph.D. degrees in Computer Science from the University of Science and Technology of China in 1996 and 2001, respectively. He joined Microsoft Research Asia in July 2001, working on data mining, social computing and ubiquitous computing. During the past years, he has published over 300 referred journal and conference papers, won the best student paper award in KDD 2016, and the best paper awards in ICDM 2013 and UIC 2010. He has more than 50 patents filed or granted. He has been invited to give keynote speeches at MDM 2019, HHME 2018, ASONAM 2017, MobiQuitous 2016, SocInfo 2015, W2GIS 2011, etc. He currently serves on the editorial boards of ACM Transactions on Social Computing (TSC), ACM Transactions on Intelligent Systems and Technology (TIST), Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT), Springer GeoInformatica, Elsevier Pervasive and Mobile Computing, CCF Transactions on Pervasive Computing and Interaction (CCF TPCI). In recent years, he was involved in the program or organizing committees of over 70 conferences and workshops. Especially, he served as program co-chair of ACM Ubicomp 2011, the 8th Chinese Pervasive Computing Conference (PCC 2012), the 12th IEEE International Conference on Ubiquitous Intelligence and Computing (UIC 2015), and the 6th National Conference on Social Media Processing (SMP 2017), and will be a program co-chair of ACM SIGSPATIAL 2020. In Oct. 2009, he founded the SIGSPATIAL China chapter which was the first regional chapter of ACM SIGSPATIAL. He is a senior member of ACM and the IEEE, and a distinguished member of China Computer Federation (CCF).

    Shirui Pan

    Monash University

    Title of Keynote: Towards Dynamic and Efficient Graph Neural Networks
    Abstract: Recent years have witnessed a wide range of applications (e.g., social networks, citation networks, and biological networks) where the data exhibits complex relation and inter-dependency among objects. Learning from graph data has imposed significant challenges to traditional machine learning algorithms, which mostly require that the data are in forms of vector format. Graph neural networks have recently emerged as a new learning paradigm to many graph analytics tasks such as classification, clustering, and link prediction. In this talk, I will briefly connect the graph neural networks (GNNs) to existing RNN or CNN architectures. As GNNs mostly focus on static graphs, I will talk about our recent study on dynamic GNN which models spatial-temporal graphs. This model can be used for traffic speed prediction, human activity recognition and taxi flow prediction. Inspired by GNNs, I will next introduce how to learn discrete network embedding to reduce storage cost and increase computational efficiency. Future directions of GNNs will be also highlighted.
    Biography: Shirui Pan is a Lecturer (a.k.a. Assistant Professor) with the Machine Learning Group, Faculty of Information Technology, Monash University. Prior to this, he was a Lecturer with the Centre for Artificial Intelligence (CAI), School of Software, University of Technology Sydney(UTS). Shirui received his Ph.D degree in computer science from UTS, Australia. To date, Dr Pan has published over 80 research papers in top-tier journals and conferences, including the IEEE Transactions on Neural Networks and Learning Systems (TNNLS), IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Transactions on Cybernetics (TCYB), ICDE, AAAI, IJCAI, ICDM, SDM, PAKDD. He is a program committee member and an invited reviewer for many top conferences and journals including NeurIPS, KDD, ICML, TPAMI, and TKDE. Dr Pan's research interests include data mining and machine learning, specialized in graph mining and network analysis.

    Important Dates


    Submission Deadline: July 31, 2019

    Acceptance Notification: September 6, 2019

    Workshop Date: November 7, 2019


    Workshop Organizers

    Huawei Shen

    Institute of Computing Technology, Chinese Academy of Sciences, China,

    Jian Tang

    HEC Montreal and Montreal Institute for Learning Algorithms, Canada,

    Peng Bao

    Beijing Jiaotong University, China,

    Program Committee


    Peng Cui , Tsinghua University
    Yuxiao Dong , Microsoft Research, Redmond
    Meng Jiang , University of Notre Dame
    Zhiyuan Liu , Tsinghua University
    Shenghua Liu , Chiense Academy of Sciences
    Chuan Shi , Beijing University of Posts and Telecommunications
    Jie Tang , Tsinghua University
    Junchi Yan , Shanghai Jiao Tong University
    Chao Zhang , Georgia Tech
    Xin Zhao , Renmin University of China
    Cheng Yang , Tsinghua University
    Jinhua Gao , Chinese Academy of Sciences
    Guojie Song, , Peking University
    Zhongying Zhao , Shandong University of Science & Technology
    Chuan Zhou , Chinese Academy of Sciences
    Huayu Wan , Beijing Jiaotong University
    Yongqing Wang , Chinese Academy of Sciences
    Xiaofei Zhu , Chongqing University of Technology
    Xiao Wang , Beijing University of Posts & Telecommunications
    Pengfei Wang , Beijing University of Posts & Telecommunications