Our world is networked: people are closer to each other through online social network services or mobile communication networks, while information is capable to be exchanged faster by World Wide Web or email networks. The social network is a treasure trove of user experiences and knowledge that presents great opportunities to understand the fundamental science of our world. In turn, many prediction tasks on nodes and edges have attracted considerable attention from both industry and academia. However, these tasks require careful effort in engineering features used by learning algorithms. While social network features require high computational resources and hard domain knowledge, it is critical to address the problem of learning network features automatically. Recent research in the broader field of network embedding, also known as representation learning for networks, has led to significant progress in automating prediction by learning the features themselves. The goal of network embedding is to project a network into a low-dimensional space, where each node can be presented as a single point in the learned latent space. However, many social network properties can not be captured by general network embedding algorithms. For instance, social networks are dynamic over time, while in most cases they are scale-free. This session aims to provide a forum for presenting the most recent advances in representation learning for social networks. We expect novel research on either frontier algorithms and models, or novel applications of network embedding on link prediction, fraud detection, network analysis, user modeling, and so on.
Jie Tang(Tsinghua University)
Title: Online Red Packets: A Large-scale Empirical Study of Gift Giving on WeChat
Jie Tang is an associate professor at Tsinghua University. He received the PhD degree in Computer Science from Tsinghua University in 2006. His research interests include social network mining and semantic web. He has published 60+ conference/journal papers and three book chapters, and filed seven patents. He has served as a PC member of 40+ conferences including WWW, SIGKDD, SIGIR, and ACL and as a reviewer of TKDE, TKDD, TNN, TALIP, and TSMC.
Huawei Shen(Chinese Academy of Science)
Title: DeepHawkes: Bridging the Gap between Prediction and Understanding of Information Cascades
Huawei Shen is a full professor in the Institute of Computing Technology, Chinese Academy of Sciences (CAS). He received his Ph.D degree in 2010 from the Institute of Computing Technology, CAS. His main research interests include social media analytics, network data mining and scientometrics. He has published more than 100 papers in prestigious journals and top-tier conferences. He served as Program Member of many conferences, including WWW, AAAI, IJCAI, SIGIR, CIKM, WSDM, ICWSM. He also served as reviewers of PNAS, Scientific Reports, PLoS ONE, Phys. Rev. E, IEEE TKDE and ACM TKDD. He received the Early Career Award of CAS and was awarded the first-class prize for Chinese Information Processing by CIPS.
Yang Yang(Zhejiang University)
Title: Network Embedding by Preserving Macroscopic Properties
Yang Yang is an assistant professor at College of Computer Science and Technology, Zhejiang University. His research focuses on mining deep knowledge from large-scale social and information networks. He obtained his Ph.D. degree from Tsinghua University in 2016, advised by Jie Tang and Juanzi Li. He has published over 20 papers in top conference/journals such as KDD, AAAI, TKDD, ICDM, etc. He has been visiting Cornell University (working with John Hopcroft) in 2012, and University of Leuven (working with Marie-Francine Moens) in 2013. He served as PC members in WWW’17, WSDM’16’17, CIKM’16’17, ICWSM’17, and ASONAM’15.
Title: Heterogeneous information network based recommendation
Chuan Shi is a professor of the Beijing University of Posts and Telecommunications and the deputy director of the Beijing Key Lab of Intelligent Telecommunications Software and Multimedia at present. He received the B.S. degree from the Jilin University in 2001, the M.S. degree from the Wuhan University in 2004, and Ph.D. degree from the ICT of Chinese Academic of Sciences in 2007. After that, he joined the Beijing University of Posts and Telecommunications as a lecturer. His research interests are in data mining, machine learning, social network analysis and evolutionary computation. He has published more than 50 papers in refereed journals and conferences, including IEEE TKDE, ACM TIST, DKE, KAIS, KDD, SDM, ECML, CIKM. He won the best paper award in ADMA2011 and Excellence Award of CCF-Tencent Xi’niu’niao fund. With his guidance, his students won champion in the IJCAI Contest 2015. He is the recipient of the Youth Talent Plan in Beijing.
Hongxia Yang(Alibaba Group)
Title: Towards a New Framework of Deep Graph Computing, Learning and Inference
Dr. Hongxia Yang is working as the Senior Staff Data Scientist and Director in Data Technology and Product Division, Alibaba Group. Her interests span the areas of Bayesian statistics, time series analysis, spatial-temporal modeling, survival analysis, machine learning, data mining and their applications to problems in business analytics and big data. Current on-going projects in her team include huge dynamic multi-level heterogenous graphical model for user profiling system, large-scale distributed knowledge graph and its efficient inference for data enabling platform and general ensemble prediction framework for various revenue and costs forecasting, among several others. She used to work as the Principal Data Scientist at Yahoo! Inc and Research Staff Member at IBM T.J. Watson Research Center respectively and got her PhD degree in Statistics from Duke University in 2010. She has published close to 30 top conference and journal papers and held 9 filed/to be filed US patents and is serving as the associate editor for Applied Stochastic Models in Business and Industry. She has been been elected as an Elected Member of the International Statistical Institute (ISI) in 2017.
Title: Question Answering in Information Networks
Dr Bin Cao is the co-founder and CTO of eigentech.ai, an AI company working on brining AI to content creation industry. He obtained his PhD from the Hong Kong University of Science and Technology on 2011. He joined Microsoft Research Asia after graduation. Later he was transferred to a product group in USA, where he built the initial language understanding models for Cortana.