I’m currently a final year Ph.D. candidate (2020 Summer - Now) in Computer Science and Engineering at the University of Notre Dame, advised by Dr. Fanny Ye. Before that, I received my B.S. and M.S. at Case Western Reserve University, supervised by Dr. Soumya Ray.

My research interest lies in graph machine learning, recommender systems, and natural language processing. I especially enjoy deriving graph learning solutions (simple, efficient, and effective) to solve real-world problems, such as product/friend recommendation, user behavior modeling, and question answering.

I will join Snap Research as a full-time research engineer, following my graduation next year. I will work in the User Modeling & Personalization team and continue my research on graph machine learning and recommender systems.

News

• [2023.09] One first-authored paper about test-time augmentation for GNNs has been accepted to NeurIPS’23. See you in New Orleans.
• [2023.09] I will serve as PCs for ICLR’24, WWW’24, SDM’24, and AAAI’24.
• [2023.01] Three papers are accepted to ICLR’23! One first-authored one studies multi-task self-suerpvised graph learning. The others study large language models for QA and graph adversarial learning. Congrats to everyone involved!
• [2022.11] One first-authored paper about graph adversarial attack has been accepted to AAAI’23.
• [2022.10] One first-authored paper on open-domain question answering has been accepted to EMNLP’22. Big thanks to my collaborators and mentors!

Professional Experiences

• Research Intern, Snap Research, Seattle, WA, USA
  Focus: Efficient Graph Neural Networks for Recommender Systems
  Mentors: Tong Zhao, Neil Shah, and Yozen Liu
  June - September, 2023

Selected Publications

[Full List] [Google Scholar]

• GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation
  M. Ju, T. Zhao, W. Yu, N. Shah, Y. Ye
  NeurIPS 23 [pdf] [code]

• Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
  M. Ju, T. Zhao, Q. Wen, W. Yu, N. Shah, Y. Ye, C. Zhang
  ICLR 23 [pdf] [code]

• Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning
  M. Ju, Y. Fan, C. Zhang, Y. Ye
  AAAI 23 [pdf] [code]

• Grape: Knowledge Graph Enhance Passage Reader for Open-domain Question Answering
  M. Ju*, W. Yu*, T. Zhao, C. Zhang, Y. Ye
  EMNLP 22 (Findings) [pdf] [code]

• Adaptive Kernel Graph Neural Network
  M. Ju, S. Hou, Y. Fan, J. Zhao, Y. Ye, L. Zhao
  AAAI 22 [pdf] [code]

• Heterogeneous Temporal Graph Neural Network
  Y. Fan, M. Ju, C. Zhang, Y. Ye
  SDM 22 [pdf] [code]

* stands for equal contribution.

Contact

• Email: mju2 [at] nd [dot] edu
• Office: 247 Fitzpatrick Hall of Engineering
• Location: University of Notre Dame, Notre Dame, IN 46565