Haiyang Yu

Applied Scientist, Amazon Web Services

haiyangyu1998 [AT] gmail.com

Bio

Howdy! I am an Applied Scientist at Amazon Web Services (AWS), where I work on Guardrails for large language model (LLM) safety and, with the GraphStorm team, on a large-scale graph machine learning (GML) framework. I received my Ph.D. from the Department of Computer Science & Engineering at Texas A&M University in December 2025, advised by Prof. Shuiwang Ji in the Data Integration, Visualization, and Exploration (DIVE) Laboratory. Before that, I obtained my bachelor’s degree from the School of Information Science and Technology, University of Science and Technology of China (USTC) in 2020.

My research focuses on (1) LLM safety, (2) trustworthy AI, (3) graph neural networks, and (4) AI for science. My work on GNN explainability, including a taxonomic survey and SubgraphX, has received over 2,000 citations. I also co-developed DIG (2k+ GitHub stars), a library for graph deep learning research, and AIRS (700+ GitHub stars), a collection of algorithms and benchmarks for AI for science.

News

Publications [selected] [Google Scholar]

* indicates equal contribution, and ** denotes equal senior contribution.

2025

Learning to Discover Regulatory Elements for Gene Expression Prediction

Xingyu Su*, Haiyang Yu*, Degui Zhi, Shuiwang Ji

International Conference on Learning Representations (ICLR Oral), 2025

Paper
2024

Equivariant Graph Network Approximations of High-Degree Polynomials for Force Field Prediction

Zhao Xu*, Haiyang Yu*, Montgomery Bohde, Shuiwang Ji

Transactions on Machine Learning Research (TMLR Featured), 2024

Paper

NetInfoF Framework: Measuring and Exploiting Network Usable Information

Meng-Chieh Lee, Haiyang Yu, Jian Zhang, Vassilis N. Ioannidis, Xiang song, Soji Adeshina, Da Zheng, Christos Faloutsos

International Conference on Learning Representations (ICLR Spotlight), 2024

Paper

Your Neighbors Are Communicating: Towards Powerful and Scalable Graph Neural Networks

Meng Liu, Haiyang Yu, and Shuiwang Ji

Transactions on Machine Learning Research (TMLR), 2024

Paper Paper collection
2023

QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules

Haiyang Yu*, Meng Liu*, Youzhi Luo, Alex Strasser, Xiaofeng Qian, Xiaoning Qian, Shuiwang Ji

Neural Information Processing Systems (NeurIPS), Track on Datasets and Benchmarks, 2023

Paper Code

Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian

Haiyang Yu, Zhao Xu, Xiaofeng Qian**, Xiaoning Qian**, Shuiwang Ji**

International Conference on Machine Learning (ICML), 2023

Paper Code
2022

Explainability in graph neural networks: A taxonomic survey

Hao Yuan, Haiyang Yu, Shurui Gui, Shuiwang Ji

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022

Paper Code

Frontiers of Graph Neural Networks with DIG

Shuiwang Ji*, Meng Liu*, Yi Liu*, Youzhi Luo*, Limei Wang*, Yaochen Xie*, Zhao Xu*, Haiyang Yu*

ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2022

Hands-on Tutorial

Paper Code Slides Video

GraphFM: Improving Large-Scale GNN Training via Feature Momentum

Haiyang Yu*, Limei Wang*, Bokun Wang*, Meng Liu, Shuiwang Ji

International Conference on Machine Learning (ICML), 2022

Paper Paper collection
2021

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

Meng Liu*, Youzhi Luo*, Limei Wang*, Yaochen Xie*, Hao Yuan*, Shurui Gui*, Haiyang Yu*, Zhao Xu, Jingtun Zhang, Yi Liu, Keqiang Yan, Haoran Liu, Cong Fu, Bora Oztekin, Xuan Zhang, and Shuiwang Ji

Journal of Machine Learning Research (JMLR), 2021

Join the DIG slack community!

Paper Code Documentation

On explainability of graph neural networks via subgraph explorations

Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, Shuiwang Ji

International Conference on Machine Learning (ICML), 2021

Paper Code
Preprint

Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems

Xuan Zhang*, Limei Wang*, Jacob Helwig*, Youzhi Luo*, Cong Fu*, Yaochen Xie*, Meng Liu, Yuchao Lin, Zhao Xu, Keqiang Yan, Keir Adams, Maurice Weiler, Xiner Li, Tianfan Fu, Yucheng Wang, Haiyang Yu, YuQing Xie, Xiang Fu, Alex Strasser, Shenglong Xu, Yi Liu, Yuanqi Du, Alexandra Saxton, Hongyi Ling, Hannah Lawrence, Hannes Stärk, Shurui Gui, Carl Edwards, Nicholas Gao, Adriana Ladera, Tailin Wu, Elyssa F. Hofgard, Aria Mansouri Tehrani, Rui Wang, Ameya Daigavane, Montgomery Bohde, Jerry Kurtin, Qian Huang, Tuong Phung, Minkai Xu, Chaitanya K. Joshi, Simon V. Mathis, Kamyar Azizzadenesheli, Ada Fang, Alán Aspuru-Guzik, Erik Bekkers, Michael Bronstein, Marinka Zitnik, Anima Anandkumar, Stefano Ermon, Pietro Liò, Rose Yu, Stephan Günnemann, Jure Leskovec, Heng Ji, Jimeng Sun, Regina Barzilay, Tommi Jaakkola, Connor W. Coley, Xiaoning Qian, Xiaofeng Qian, Tess Smidt, Shuiwang Ji

Paper Code

Services

Program Committee Member & Reviewer [Selected]

International Conference on Machine Learning (ICML) 2021, 2022

International Conference on Learning Representation (ICLR) 2023

Learning on Graphs Conference (LoG) 2022

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Vitæ

Here is my CV[PDF].

  • Amazon Web Services Aug 2025 - now
    Applied Scientist
    Guardrails for LLM safety
    GraphStorm team: large-scale graph machine learning (GML) framework
  • Texas A&M University Aug 2024 - Dec 2024
    Graduate Assistant Lecturer
  • Amazon Web Service June 2023 - Aug 2023, June 2024 - Aug 2024
    Applied Scientist Intern
    Mentor: Dr. Xiang Song
  • Texas A&M University Aug 2020 - Dec 2025
    Ph.D. in Computer Engineering
    Advisor: Prof. Shuiwang Ji
    Computer Science & Engineering
  • University of Sydney July 2019 - Sept 2019
    Visiting Student
    Advisor: Dr. Jing Zhang, Prof. Dacheng Tao
    Computer Science
  • USTC Aug 2016 - Jul 2020
    B.E. Student
    Electronic Engineering and Information Science, University of Science and Technology of China
Haiyang Yu
based on the templates by Meng Liu, Martin Saveski and Paul J. Wright