Jaemin Yoo

Ph.D. Student at Seoul National University

Jaemin Yoo

Data Mining Laboratory
Computer Science and Engineering
Seoul National University (SNU)
Tel: +82-2-880-7263
Email: jaeminyoo@snu.ac.kr
[ Download C.V. ]
[ Google Scholar | DBLP | Facebook ]

About Me

I am a Ph.D. student majoring in Computer Science and Engineering at Seoul National University, advised by Prof. U Kang. My research interests include data mining and machine learning. I am a recipient of the Google PhD Fellowship Program in Machine Learning.

Research Interests

  • Machine learning on graphs (ICDM'17, WSDM'18, IJCAI'19, WSDM'20)
  • Interpretable machine learning (ICDM'19)
  • Neural network compression (NeurIPS'19)

Education

  • Ph.D. Student (Mar. 2016 - Present)
  • Bachelor of Science (Feb. 2016)
    Computer Science and Engineering
    Seoul National University

Awards and Honors

  • Google PhD Fellowship Program (Machine Learning, Sep. 2019)
  • Samsung HumanTech Paper Award (Honorable Mention; 4th in CS, Feb. 2019)
  • Google Travel and Conference Grants (Nov. 2017)

Publications

Conferences

  • Sampling Subgraphs with Guaranteed Treewidth for Accurate and Efficient Graphical Inference
    Jaemin Yoo, U Kang, Mauro Scanagatta, Giorgio Corani, and Marco Zaffalon
    WSDM 2020
    (acceptance rate 91/615 = 14.8%)
  • EDiT: Interpreting Ensemble Models via Compact Soft Decision Trees
    Jaemin Yoo and Lee Sael
    ICDM 2019 [ paper | github | slides | bib ]
    (acceptance rate 194/1046 = 18.5%)
  • Belief Propagation Network for Hard Inductive Semi-Supervised Learning
    Jaemin Yoo, Hyunsik Jeon, and U Kang
    IJCAI 2019 [ paper | github | slides | poster | bib ]
    (acceptance rate 850/4752 = 17.9%)
  • Fast and Scalable Distributed Loopy Belief Propagation on Real-World Graphs
    Saehan Jo, Jaemin Yoo, and U Kang
    WSDM 2018 [ paper | homepage | slides | poster | bib ]
    (acceptance rate 83/514 = 16.3%)
  • Supervised Belief Propagation: Scalable Supervised Inference on Attributed Networks
    Jaemin Yoo, Saehan Jo, and U Kang
    ICDM 2017 [ paper | homepage | slides | bib ]
    Regular paper (acceptance rate 72/778 = 9.3%)

Journals