معرفی
Rex Ying is an Assistant Professor of Computer Science at Yale University, where he leads the Graph and Geometric Learning Lab. His research focuses on developing expressive, scalable, and explainable algorithms for graph-structured data through graph neural networks and geometric learning.
His educational background includes:
- Ph.D. in Computer Science from Stanford University
- B.S. in Computer Science from Duke University
Ying's research spans graph neural networks, geometric deep learning, and non-Euclidean foundation models. His work addresses the challenge of representing real-world data expressed as graphs, with applications in recommender systems, anomaly detection, social network analysis, protein networks, drug discovery, and physical simulations. He develops techniques that combine relational reasoning, multimodal learning, and foundation models to create efficient and scalable approaches for complex real-world data beyond just text and images.
Analysis of his publication record shows a strong focus on advancing graph representation learning, with particular emphasis on hyperbolic geometry for hierarchical data, explainability of graph neural networks, and applications across diverse domains including biology, physics, and social sciences. His work demonstrates a consistent trajectory from theoretical foundations to practical implementations.
His scientific achievements include:
- Baidu Scholarship 2019
- Area Chair for LoG 2022 Conference
- Co-Lead of PyTorch Geometric Library for GNNs
- Lead organizer of SimDL Workshop at ICLR 2021
- Blue Sky Best Paper Award at ACM KDD 2025 for RephQA
Ying actively mentors students and researchers, seeking Ph.D. candidates passionate about pushing frontiers in GNNs and geometric deep learning. He has received funding including an NSF core program award on building foundation models for scientific discovery. His lab collaborates across disciplines, working on applications in biology, medicine, chemistry, physics, neuroscience, social networks, and supply chain.
The Graph and Geometric Learning Lab focuses on three main research thrusts: Geometric and Graph Learning, Multimodal Foundation Models, and Trustworthy AI, with applications spanning multiple scientific domains.
