Dr. Ma’s research spans machine learning, natural language processing, and biomedical research. He is particularly interested in exploring and modeling relational structures of data, especially the graphs that characterize interactions of a complex system. His work on graph learning includes scalable graph learning, graph coarsening, dynamic graph learning, graph neural networks enhanced by geometry and topology, and various applications to the biomedical domain. He also works on time series analysis, summarization, and AI4code.