About me

I am a fourth-year PhD student at Stevens Institute of Technology (2021–present), advised by Prof. Yue Ning. My research centers on Graph Neural Networks (GNNs), with a focus on developing robust and trustworthy models that can adapt to diverse scenarios and overcome real-world challenges. Specifically, my work addresses critical issues such as catastrophic forgetting in continual learning, out-of-distribution (OOD) generalization under distribution shifts, and graph privacy protection against adversarial attacks with Differential Privacy (DP).

I am also enthusiastic about applying GNNs and other advanced machine learning methods to solve real-world problems across domains such as societal event prediction and Electronic Health Record (EHR) prediction. My work on permeability prediction with GNNs also highlights the potential of cutting-edge deep learning techniques in AI for science.

With the rapid advancements in Large Language Models (LLMs), I see immense potential in leveraging them to enhance the generalizability of GNNs. I am also eager to explore Graph Foundation Models.

Feel free to reach out if you share similar research interests or have innovative ideas in these areas. I am always open to discussions and collaborations!

News

• 2025.1, Paper on graph OOD generalization accepted by AISTATS 2025.
• 2024.11, I received NeurIPS 2024 Scholar Award.
• 2025.11, Paper on EHR prediction accepted by IEEE BigData 2024 Workshop on Big Data and AI for Healthcare.
• 2024.9, Paper on Continual Graph Learning accepted by NeurIPS 2024.
• 2024.4, I passed my Defense Proposal. Officially a PhD candidate!
• 2022.10, I received the ICDM 20222 Student Travel Award.
• 2022.8, Paper on social event prediction accepted by ICDM 2022.
• 2022.8, I passed my oral qualification exam.

Education

• Stevens Institute of Technology, Ph.D in Computer Science, 2021 - Now
• Virginia Tech, M.S. in Mechanical Engineering, 2018 - 2020
• University of Arizona, B.S. in Mechanical Engineering, 2014 - 2018