Dongmian Zou

Dongmian Zou received the B.S. degree in Mathematics (First Honour) from the Chinese University of Hong Kong in 2012 and the Ph.D. degree in Applied Mathematics and Scientific Computation from the University of Maryland, College Park in 2017. From 2017 to 2020, he served as a post-doctorate researcher at the Institute for Mathematics and its Applications, and the School of Mathematics at the University of Minnesota, Twin Cities. He joined Duke Kunshan University in 2020 where he is currently an Assistant Professor of Data Science in the Division of Natural and Applied Sciences. He is also affiliated with the the Zu Chongzhi Center for Mathematics and Computational Sciences (CMCS) and the Data Science Research Center (DSRC). His research is in the intersection of applied harmonic analysis, machine learning and signal processing. His current interest includes geometric deep learning, robustness, anomaly detection, and applications in e.g., communication, circuits and medical imaging.

Current Appointments & Affiliations

Assistant Professor of Data Science at Duke Kunshan University · 2020 - Present DKU Faculty

Assistant Professor of the Practice of Interdisciplinary Studies at DKU Unit at Duke University · 2026 - Present Interdisciplinary Studies at DKU Unit, DKU Faculty

Recent Publications

Ensemble Pruning via Graph Neural Networks

Conference Cikm 2025 Proceedings of the 34th ACM International Conference on Information and Knowledge Management · November 10, 2025 Ensemble learning is a pivotal machine learning strategy that combines multiple base learners to achieve prediction accuracy surpassing that of any individual model. Despite its effectiveness, large-scale ensemble learning consumes a considerable amount of ... Full text Cite

Enhancing Fairness in Autoencoders for Node-Level Graph Anomaly Detection

Conference Frontiers in Artificial Intelligence and Applications · October 21, 2025 Graph anomaly detection (GAD) has become an increasingly important task across various domains. With the rapid development of graph neural networks (GNNs), GAD methods have achieved significant performance improvements. However, fairness considerations in ... Full text Cite

Improving Hyperbolic Representations via Gromov-Wasserstein Regularization

Chapter · January 1, 2025 Hyperbolic representations have shown remarkable efficacy in modeling inherent hierarchies and complexities within data structures. Hyperbolic neural networks have been commonly applied for learning such representations from data, but they often fall short ... Full text Cite

View All Publications

Education, Training & Certifications

University of Maryland, College Park · 2017 Ph.D.

External Links

Google Scholar