About

I’m a Member of Technical Staff at Inflection AI / Microsoft AI, where my research focuses on post-training with tool use. My work spans fundamental research in agent post-training to shipping the tool-usage framework in Copilot, gaining full-stack experience from research through to product deployment.

Previously, I was a PhD student in the Computer Science Department at Carnegie Mellon University, advised by Prof. Christos Faloutsos and Prof. Ruslan Salakhutdinov. My PhD was supported by the Amazon Graduate Research Fellowship and the Kwanjeong Educational Foundation Scholarship. Before joining CMU, I received my bachelor’s and master’s degrees from Seoul National University, South Korea.

Work Experiences

  • Inflection AI / Microsfot AI
    Member of Technical Staff, AI (Feb. 2024 - Present)
    Post training for tool-use and agent
  • Amazon Web Services
    Research Intern (May. 2023 - Aug. 2023)
    Heterogeneous graph learning powered by pretrained LLMs
  • Google Research
    Research Intern (May. 2021 - Aug. 2021)
    Transfer learning between different node types on a heterogeneous graph
  • LinkedIn
    Research Intern (May. 2020 - Aug. 2020)
    Developed an algorithm to optimize computation graphs in Graph Neural Networks
  • Amazon.com
    Research Intern (May. 2019 - Aug. 2019)
    Developed a fast and scalable algorithm for fraud detection in Amazon.com
  • SAP Labs Korea
    Software Developer (Sep. 2014 - Mar. 2017)
    Developed an in-memory database SAP HANA

Publication

  • Multimodal Graph Learning for Generative Tasks
    Minji Yoon, Jing Yu Koh, Bryan Hooi, Russ Salakhutdinov
    NeurIPS workshop on New Frontiers in Graph Learning (NeurIPS-GLFrontiers), 2023
    [Paper] [Code]
  • Graph Generative Model for Benchmarking Graph Neural Networks
    Minji Yoon, Yue Wu, John Palowitch, Bryan Perozzi, Russ Salakhutdinov
    International Conference on Machine Learning (ICML) 2023
    [Paper] [Code]
    ** Selected as an outstanding paper at the Workshop on Graph Learning Benchmarks (KDD-GLB) 2023
  • Automatic Question-Answer Generation for Long-Tail Knowledge
    Youngmin Kim*, Rohan Kumar*, Sunitha Ravi*, Haitian Sun, Christos Faloutsos, Ruslan Salakhutdinov, Minji Yoon
    KDD Workshop on Knowledge Augmented Methods for Natural Language Processing (KDD-KnowledgeNLP) 2023
    [Paper]
  • A Dataset on Malicious Paper Bidding in Peer Review
    Steven Jecmen, Minji Yoon, Vincent Conitzer, Nihar B. Shah, Fei Fang
    The Web Conference 2023
    [Paper] [Arxiv]
  • Toward more Practical Deep Learning on Graphs
    Minji Yoon, Thesis Proposal 2022
    Thesis Committee: Christos Faloutsos (CMU), Ruslan Salakhutdinov (CMU), Tom M. Mitchell (CMU), Jure Leskovec (Stanford university)
  • Zero-shot Transfer Learning on Heterogeneous Graphs via Knowledge Transfer Networks
    Minji Yoon, John Palowitch, Dustin Zelle, Ziniu Hu, Ruslan Salakhutdinov, Bryan Perozzi
    Neural Information Processing Systems (NeurIPS) 2022
    [Paper] [Arxiv] [Code] [Slide] [DLG workshop 2022] [Google AI blog]
  • Autonomous Graph Mining Algorithm Search with Best Performance Trade-off
    Minji Yoon, Theophile Gervet, Bryan Hooi, Christos Faloutsos
    SCIE Journal, Knowledge and Information Systems (KAIS) 2022
    [Paper] [shorter ver.] [Code] [Slide]
  • 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
    [Paper] [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
    [Paper] [Slide] [Video] [Code] [CMU blog] [LinkedIn blog] [VentureBeat] [MarketsInsider]
  • Autonomous Graph Mining Algorithm Search with Best Speed/Accuracy Trade-off
    Minji Yoon, Theophile Gervet, Bryan Hooi, Christos Faloutsos
    20th IEEE International Conference on Data Mining (ICDM) 2020
    ** Selected as one of the best papers of ICDM’20 for a fast track journal invitation at KAIS
    [Paper] [Code] [Slide]
  • Provably Robust Node Classification via Low-Pass Message Passing
    Yiwei Wang, Shenghua Liu, Minji Yoon, Hemank Lamba, Wei Wang, Christos Faloutsos, Bryan Hooi
    20th IEEE International Conference on Data Mining (ICDM) 2020
    [Paper]
  • MIDAS: Microcluster-Based Detector of Anomalies in Edge Streams
    Siddharth Bhatia, Bryan Hooi, Minji Yoon, Kijung Shin, Christos Faloutsos
    34th AAAI Conference on Artificial Intelligence (AAAI) 2020
    [Paper]
  • Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach
    Minji Yoon, Bryan Hooi, Kijung Shin, Christos Faloutsos
    SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2019, Alaska, USA
    [Paper(updated)] [Code] [Poster]
  • Fast and Accurate Random Walk with Restart on Dynamic Graphs with Guarantees
    Minji Yoon, Woojeong Jin, U Kang
    The Web Conference (WWW) 2018, Lyon, France
    [Paper] [Code] [Slide]
  • TPA: Fast, Scalable and Accurate Method for Approximate Random Walk with Restart on Billion Scale Graphs
    Minji Yoon, Jinhong Jung, U Kang
    IEEE International Conference on Data Engineering (ICDE) 2018, Paris, France
    [Paper] [Code] [Slide]

Teaching Experiences

AWARDS & HONORS

  • Amazon Graduate Research Fellowship, Amazon (Sep. 2020 - Aug. 2023)
    Awarding the amount of $70,000 to support scientific research of graduate students per year.
  • AWS Cloud Credit for Research, AWS (Sep. 2021 - Aug. 2022)
    Awarding $19,000 AWS Cloud Credit for Research; my project "Automation and Democratization of Graph Mining" was part of the proposal.
  • Kwanjeong Educational Foundation Scholarship, Kwanjeong Foundation (Sep. 2018 - Aug. 2022)
    4 years for Doctor’s Degree.

Student Advising

Amazing students I've had the pleasure of advising:

Professional Services

Reviewer: JMLR, KDD, The Web Conference, WSDM, NeurIPS on GLFrontiers workshop