Kien T. Pham

(Vietnamese: Phạm Trung Kiên)
Email: kien.pham [at]
My Blog


  • 2016/07, our paper, titled "Interactive Exploration for Domain Discovery on the Web" got accepted to KDD Workshop on Interactive Data Exploration and Analytics 2016.
  • 2016/05, I will be interning at IBM Thomas J. Watson Research Center as part of the IBM Social Good Fellowship.
  • 2016/03, our paper, titled "Understanding Website Behavior based on User Agent" got accepted to SIGIR 2016. I also received SIGIR Travel Grant to attend the conference in Pisa, Italy.
  • 2015/04, check out Memex open catalog, an index of open source software that are being developed under Memex Program.
  • 2014/09, our paper, titled "The More the Merrier: Efficient Multiple-Source Graph Traversal" which is rooted from SIGMOD Programming Contest 2014, got accepted to VLDB 2015.
  • 2014/09, I start working on Memex program (Domain-Specific Search) that seeks to develop retrieval and analytic technologies to fight human trafficking and uncover criminal activities on the web. Initial works are available at this and this.
  • 2014/09, our paper, titled Structured Open Urban Data: Understanding the Landscape, got accepted in Big Data Journal.
  • 2014/07, our team (VIDA) got the 2nd place in SIGMOD programming contest.
  • Spring 2014, I am a TA for the Introduction to Operating System Course - CS6233.
  • 2014/01, I pass the PhD qualifying exam.
  • Fall 2013, I am a TA for the Big Data Analysis Course - CS9223.
  • Summer 2013, I am a research intern at Los Alamos National Laboratory, working with Data Science at Scale Team.


    I am a PhD student since Fall 2012 under the supervision of Professor Juliana Freire at NYU School of Engineering in Computer Science. My current research is to investigate the applications of machine learning for focused crawler. I also had worked on open data integration and multilingual inconsistency resolution in Wikipedia.
    During my undergraduate, Hanoi University of Science and Technology, I did play with Evolutionary algorithms and Spanning trees. Then I moved to System land with R&D Team at VNG Corporation, where I involved in three projects: distributed key-value storage system, social search engine, feed ranking. Before leaving the industry for graduate school, I worked on an internet start-up as founding engineer.