Haiyang Yu
Applied Scientist at Amazon Web Services (AWS)
College Station, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolHaiyang Yu is an applied scientist and 5th-year Ph.D. candidate at Texas A&M University with seven years of experience in graph deep learning, AI for science, and trustworthy AI, now working at AWS. He develops and ships research-grade tools—authoring QHNet and QH9 to enable equivariant networks for density functional theory and contributing explainability work like SubgraphX and PGExplainer integrated into the DIG graph-learning library. His work spans theory, scalable GNN systems (e.g., GraphFM for massive graphs), and practical explainability implementations, bridging academic research and production engineering. Based in College Station, he combines a strong experimental track record with open-source impact and a background from the University of Science and Technology of China, bringing domain depth in both ML methodology and scientific applications.
7 years of coding experience
Bachelor's degree Electrical and Information Engineering, Bachelor's degree Electrical and Information Engineering at University of Science and Technology of ChinaDoctor of Philosophy - PhD Computer Engineering, Doctor of Philosophy - PhD Computer Engineering at Texas A&M University
Github Skills (7)
pytorch10
machine-learning10
deep-learning10
graph-neural-network10
3d7
graph7
3d-graphics7
Programming languages (4)
Github contributions (5)
divelab/DIG
Mar 2021 - Oct 2022
A library for graph deep learning research
Role in this project:
ML Engineer
ML EngineerContributions:96 commits, 6 PRs, 77 pushes in 1 year 7 months
Contributions summary:Haiyang contributed to the development of explainable machine learning methods for graph neural networks within the `dig/dig` repository. They added PGExplainer and related packages, including code for PGExplainer, and the integration of SubgraphX. The user focused on the implementation of explanation models, including loss functions and subgraph extraction, and also included visualization updates.
explainable-mlpytorchdataminingdeep-learninggraph-deep-learning
Oceanusity/awesome-gnns-on-large-scale-graphs
Jul 2021 - Oct 2022
Contributions:23 commits, 2 PRs, 26 pushes in 1 year 3 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.