Tengfei Ma

Tengfei Ma is an Assistant Professor in the Department of Biomedical Informatics at Stony Brook University, with affiliations to Computer Science and Applied Mathematics & Statistics. He holds a Ph.D. from The University of Tokyo, M.S. from Peking University, and B.E. from Tsinghua University. Previously, he was a Research Scientist at IBM T.J. Watson Research Center. His research focuses on machine learning, natural language processing (NLP), and biomedical informatics, particularly deep graph learning, scalable graph methods, and healthcare applications. He has contributed to frameworks like EvolveGCN for dynamic graphs and IGB datasets for graph benchmarks.

Key awards include ISWC 2021 Best Paper (Research Track) and IBM Outstanding Research Accomplishments (2019, 2022). His work bridges theory and practice, addressing challenges like over-dilution in GNNs and interpretable time series analysis. Collaborations span interdisciplinary areas, such as AI for wound monitoring and code summarization. He teaches BMI530: Software Development for Biomedical Informatics and is open to graduate students from CS, BMI, and AMS departments.

Research highlights include:

• Deep Graph Learning: Scalability (FastGCN, IGB), dynamic graphs (EvolveGCN), and topology-enhanced GNNs.
• Healthcare: Models for EHR analysis, medication recommendation (GAMENet), and wearable wound monitoring.
• NLP: Document summarization, code summarization (CP-BCS), and commonsense generation via knowledge graph compression.

Recent projects include AI tools like Influencer for promotional content creation and neural-symbolic models for interpretable time series analysis. His lab explores foundational AI for healthcare, code analysis, and graph systems.