Chao Chen

Chao Chen is an Assistant Professor in the Department of Biomedical Informatics at Stony Brook University, focusing on topological data analysis (TDA) and its applications in machine learning and biomedical imaging. His work bridges theoretical insights from persistent homology and discrete Morse theory with practical challenges in robust learning and graph neural networks.

• Interests: Machine Learning, Biomedical Informatics, TDA, Persistent Homology
• Publications: Published in major machine learning and medical imaging conferences like MICCAI, NeurIPS, and CVPR.
• Service: Area chair for MICCAI, AAAI, CVPR, and NeurIPS.

His research emphasizes the geometric and topological structures of data to enhance model robustness and interpretability, particularly in digital pathology and cancer analysis. Recent work includes TopoTxR for breast cancer imaging and MERGE for gene expression prediction using hierarchical graph-based GNNs.

Key trends in his articles include leveraging TDA for adversarial robustness, spatially aware models for histopathology, and security analysis of AI systems. His methodologies often integrate theoretical guarantees with real-world biomedical applications.

Chao Chen serves as an area chair in top-tier AI conferences and contributes to advancing topological and robust machine learning paradigms in biomedical research.