About Me

Postdoc @ Stanford University

Ce is a postdoctoral researcher in Computer Science at Stanford University. He is working with Christopher Ré on data management and database systems. With the indispensable help of many collaborators, his PhD work produced the system DeepDive, a trained data system for automatic knowledge-base construction. As part of his PhD thesis, he led the research efforts that won the 2014 SIGMOD Best Paper Award and was invited to the “Best of VLDB 2015” special issue; PaleoDeepDive, a machine-reading system for paleontologists, was featured in Nature magazine, and he also led the Stanford team that produced the top-performing machine-reading system for TAC-KBP 2014 slot-filling evaluations using DeepDive. Ce obtained his PhD from the University of Wisconsin-Madison, advised by Christopher Ré, and his Bachelor of Science degree from Peking University, advised by Bin Cui.



  • Program Committee:
    •         SIGMOD: 2016 Ph.D. Symposium Workshop.
    •         VLDB: 2016 Demo.
    •         IJCAI: 2016.
    •         CIKM: 2015, 2013.
    •         WAIM: 2016; DEOS: 2014.



  • DeepDive: Declarative Knowledge Base Construction
        Christopher De Sa, Alex Ratner, Christopher Ré, Jaeho Shin, Feiran Wang, Sen Wu, and Ce Zhang
        SIGMOD Record 2016.
        SIGMOD Research Highlight
  • Extracting Databases from Dark Data with DeepDive
        Ce Zhang, Michael Cafarella, Feng Niu, Christopher Ré, and Jaeho Shin
        SIGMOD 2016 (Industrial Track, to appear).
  • Materialization Optimizations for Feature Selection
        Ce Zhang, Arun Kumar, and Christopher Ré
        TODS, 2016 (to appear).


  • DeepDive: A Data Management System for Automatic Knowledge Base Construction
        Ce Zhang
        Ph.D. Dissertation, University of Wisconsin-Madison, 2015.     Download PDF Here
  • Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries
        Yuke Zhu, Ce Zhang, Christopher Ré, and Li Fei-Fei
        arXiv pre-prints 2015.
  • Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width
        Christopher De Sa, Ce Zhang, Kunle Olukotun, and Christopher Ré
        NIPS 2015.
  • Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms
        Christopher De Sa, Ce Zhang, Kunle Olukotun, and Christopher Ré
        NIPS 2015.
  • Large-scale Extraction of Gene Interactions from Full Text Literature Using DeepDive
        Emily Mallory, Ce Zhang, Christopher Ré, and Russ Altman
        Bioinformatics 2015.
  • Caffe con Troll: Shallow Ideas to Speed Up Deep Learning
        Stefan Hadjis, Firas Abuzaid, Ce Zhang, and Christopher Ré
        DanaC 2015.
  • Incremental Knowledge Base Construction Using DeepDive
        Jaeho Shin, Sen Wu, Feiran Wang, Ce Zhang, and Christopher Ré
        VLDB, 2015.
        Invited to Special Issue on VLDB 2015
  • Stanford's Distantly Supervised Slot Filling Systems for KBP 2014
        Gabor Angeli, Sonal Gupta, Melvin Johnson Premkumar, Chris Manning,
        Chris Re, Julie Tibshirani, Jean Y. Wu, Sen Wu, and Ce Zhang
        Text Analysis Conference Proceedings, 2015


  • A Machine Reading System for Assembling Synthetic Paleontological Databases
        Shanan E. Peters, Ce Zhang, Miron Livny, and Christopher Ré
        PLoS ONE, 2014.
        Biodiversity of different biological classes compiled by PaleoDeepDive (powered by DeepDive!). See the decline of and the flourishing of !
  • Feature Engineering for Knowledge Base Construction
        DeepDive Group
        IEEE Data Engineering Bulletin 2014
  • Parallel Feature Selection Inspired by Group Testing
        Yingbo Zhou, Utkarsh Porwal, Ce Zhang, Hung Q. Ngo, Long Nguyen, Christopher Ré, and Venu Govindaraju
        NIPS 2014
  • Tradeoffs in Main-Memory Statistical Analytics: Impala to DimmWitted (Invited)
        Victor Bittorf, Marcel Kornacker, Christopher Ré, and Ce Zhang
        IMDM 2014
  • DimmWitted: A Study of Main-Memory Statistical Analytics
        Ce Zhang, and Christopher Ré
        VLDB, 2014.
        DimmWitted is the "secret sauce" that enables DeepDive to process billions of random variables everyday tirelessly. Stay tuned for our open-source release soon!
  • Materialization Optimizations for Feature Selection
        Ce Zhang, Arun Kumar, and Christopher Ré
        SIGMOD, 2014.
        Best Paper Award


  • A Markov Logic Framework for Recognizing Complex Events from Multimodal Data
        Young Chol Song, Henry Kautz, James Allen, Mary Swift, Yuncheng Li, Jiebo Luo, and Ce Zhang
        ICMI, 2013.
  • An Approximate, Efficient LP Solver for LP Rounding
        Srikrishna Sridhar, Victor Bittorf, Ji Liu, Ce Zhang, Christopher Ré, and Stephen J. Wright.
        NIPS, 2013.
  • Building an Entity-Centric Stream Filtering Test Collection for TREC 2012
        John R. Frank, Max Kleiman-Weiner, Daniel A. Roberts, Feng Niu, Ce Zhang, Christopher Ré, Ian Soboroff
        TREC, 2013.
  • SHORT Understanding Tables in Context using Standard NLP Toolkits
        Vidhya Govindaraju, Ce Zhang and Christopher Ré
        ACL, 2013.
  • Towards High-Throughput Gibbs Sampling at Scale: A Study across Storage Managers
        Ce Zhang, and Christopher Ré
        SIGMOD, 2013.
  • DEMO GeoDeepDive: Statistical Inference using Familiar Data-Processing Languages
        Ce Zhang, Vidhya Govindaraju, Jackson Borchardt, Tim Foltz, Christopher Ré, and Shanan Peters
        SIGMOD, 2013.
  • VISION Brainwash: A Data System for Feature Engineering
        Michael Anderson, Dolan Antenucci, Victor Bittorf, Matthew Burgess, Michael Cafarella,
            Arun Kumar, Feng Niu, Yongjoo Park, Christopher Ré, and Ce Zhang
        CIDR, 2013.


  • SHORT Scaling Inference for Markov Logic via Dual Decomposition
        Feng Niu, Ce Zhang, Christopher Ré, and Jude Shavlik
        ICDM, 2012.
  • Big Data versus the Crowd: Looking for Relationships in All the Right Places
        Ce Zhang, Feng Niu, Christopher Ré, and Jude Shavlik
        ACL, 2012
  • Elementary: Large-scale Knowledge-base Construction via Machine Learning and Statistical Inference
        Feng Niu, Ce Zhang, Christopher Ré, and Jude Shavlik
        IJSWIS, Special Issue on Knowledge Extraction from the Web, 2012
  • DeepDive: Web-scale Knowledge-base Construction using Statistical Learning and Inference
        Feng Niu, Ce Zhang, Christopher Ré, and Jude Shavlik
        VLDS, 2012


  • Modeling User Expertise in Folksonomies by Fusing Multi-type Features
        Junjie Yao, Bin Cui, Qiaosha Han, Ce Zhang, Yanhong Zhou
        DASFAA, 2011


  • Content-enriched classifier for web video classification
        Bin Cui, Ce Zhang, Gao Cong
        SIGIR, 2011
  • Multiple feature fusion for social media applications
        Bin Cui, Anthony K. H. Tung, Ce Zhang, Zhe Zhao
        SIGMOD, 2010


  • The use of categorization information in language models for question retrievaln
        Xin Cao, Gao Cong, Bin Cui, Christian S. Jensen, Ce Zhang
        CIKM, 2009
  • A Revisit of Query Expansion with Different Semantic Levels
        Ce Zhang, Bin Cui, Gao Cong, Yu-Jing Wang
        DASFAA, 2009
  • DEMO Video Annotation System Based on Categorizing and Keyword Labelling
        Bin Cui, Bei Pan, Heng Tao Shen, Ying Wang, Ce Zhang
        DASFAA, 2009


  • POSTER Semantic similarity based on compact concept ontology
        Ce Zhang, Yu-Jing Wang, Bin Cui, Gao Cong
        WWW, 2008