What's New

  • November, 2021 - We will release PASS's source code to the public soon! Meanwhile, please reach out to me for any inquiries.
  • September, 2021 - We won $19,000 AWS Cloud Credits for Research; my project "Automation and Democratization of Graph Mining" was part of the proposal.
  • September, 2021 - I started being co-advised by Prof. Ruslan Salakhutdinov. Looking foward to what we can make together in Deep Learning on graphs.
  • June, 2021 - Our work "Graph Fraud Detection based on Accessibility Score Distributions" got accepted to ECML-PKDD 2021. This is my first single-author work.
  • May, 2021 - I will intern with Googe Research, New York this summer.
  • May, 2021 - Our work "Performance-Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks" collaborated with LinkedIn got accepted in the research track of SIGKDD 2021.
  • January, 2021 - Great News! I have been selected as a 2021 Amazon Graduate Research Fellow.

About

I am currently a PhD student at the Computer Science Department at Carnegie Mellon University, where I am advised by Prof. Christos Faloutsos and Prof. Ruslan Salakhutdinov. My research interests are in the area of Graph Mining and Deep Learning.

More specifically, I’m interested in Automation and Democratization of Graph Mining using various Deep Learning techniques. My recent work includes automation in 1) polishing/generation of graph structures, 2) generation of node/edge/subgraph representations, and 3) solution generation in the application level. Ultimately, I’d like to empower all users to benefit from Graph Mining, regardless of their level of expertise in the field.

I was a research intern at Amazon.com, LinkedIn, and Google Research. Before joining CMU, I received my bachelor’s and master’s degrees from Seoul National University, South Korea.

Publication

  • Graph Fraud Detection Based on Accessibility Score Distributions
    Minji Yoon
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) 2021
    [PDF] [Code] [Slide]
  • Performance-Adaptive Sampling Strategy Towards Fast and Accurate Graph Neural Networks
    Minji Yoon, Theophile Gervet, Baoxu Shi, Sufeng Niu, Qi He, Jaewon Yang
    SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2021
    [PDF] [Slide] [Video]
    **Thanks for a lot of attention to our method, PASS. Currently, our code is under process to be public (we expect late 2021 or early 2022). Meanwhile, please reach out to me via my email to ask any inquiries about implementation.
  • Autonomous Graph Mining Algorithm Search with Best Speed/Accuracy Trade-off
    Minji Yoon, Theophile Gervet, Bryan Hooi, and Christos Faloutsos
    20th IEEE International Conference on Data Mining (ICDM) 2020
    (Acceptance Ratio: 9.8%)
    **Selected as one of the best papers of ICDM’20 for a fast track journal invitation at KAIS
    [PDF] [Code] [Slide]
  • Provably Robust Node Classification via Low-Pass Message Passing
    Yiwei Wang, Shenghua Liu, Minji Yoon, Hemank Lamba, Wei Wang, Christos Faloutsos, and Bryan Hooi
    20th IEEE International Conference on Data Mining (ICDM) 2020
    (Acceptance Ratio: 9.8%)
    [PDF]
  • MIDAS: Microcluster-Based Detector of Anomalies in Edge Streams
    Siddharth Bhatia, Bryan Hooi, Minji Yoon, Kijung Shin, and Christos Faloutsos
    34th AAAI Conference on Artificial Intelligence (AAAI) 2020
    [PDF]
  • Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach
    Minji Yoon, Bryan Hooi, Kijung Shin, and Christos Faloutsos
    SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2019, Alaska, USA
    [PDF(old)] [PDF(updated)] [Code] [Poster]
  • Fast and Accurate Random Walk with Restart on Dynamic Graphs with Guarantees
    Minji Yoon, Woojeong Jin, and U Kang
    The Web Conference (WWW) 2018, Lyon, France
    (Acceptance Ratio: 14.8%)
    [PDF] [Code] [Slide]
  • TPA: Fast, Scalable and Accurate Method for Approximate Random Walk with Restart on Billion Scale Graphs
    Minji Yoon, Jinhong Jung, and U Kang
    IEEE International Conference on Data Engineering (ICDE) 2018, Paris, France
    [PDF] [Code] [Slide]

Work Experiences

  • Graph Mining team, Google Research
    Research Intern (May. 2021 - Aug. 2021)
    Transfer learning between different node types on a heterogeneous graph
  • Standardization team, LinkedIn
    Machine Learning Engineer Intern (May. 2020 - Aug. 2020)
    Developed an algorithm to optimize computation graphs in Graph Neural Networks (GNNs)
  • CTPS Machine Learning Accelation team, Amazon.com
    Applied Scientist Intern (May. 2019 - Aug. 2019)
    Developed a fast and scalable algorithm for fraud detection in Amazon.com
  • Data Mining Lab, Seoul National University
    Research Intern (Apr. 2017 - Jun. 2018)
    Developed fast, accurate and scalable algorithms for Random Walk with Restart (RWR)
  • Session team, SAP Labs Korea
    Software Developer (Sep. 2014 - Mar. 2017)
    Developed an in-memory database SAP HANA

AWARDS & HONORS

  • AWS Cloud Credit for Research, AWS (Sep. 2021)
    Awarding $19,000 AWS Cloud Credit for Research; my project "Automation and Democratization of Graph Mining" was part of the proposal.
  • Amazon Graduate Research Fellowship, Amazon (Sep. 2021 - Aug. 2022)
    Awarding the amount of $70,000 to support scientific research of Masters/PhD students.
  • Kwanjeong Educational Foundation Scholarship, Kwanjeong Foundation (Sep. 2018 - Aug. 2022)
    4 years for Doctor’s Degree.
  • National Science & Technology Scholarship, KOSAF (Mar. 2008 - Feb. 2012)
    Full tuition exemptions for 8 semesters.
  • Cum Laude Graduation Honors, Seoul National University (Feb. 2012)