Scholars@Duke
Dongmian Zou

Dongmian Zou

Assistant Professor of Data Science at Duke Kunshan University
DKU Faculty

Scholarly Works - Conferences

Enhancing Node-Level Graph Domain Adaptation by Alleviating Local Dependency

Conference Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · April 20, 2026 Recent years have witnessed significant advancements in machine learning methods on graphs. However, transferring knowledge effectively from one graph to another remains a critical challenge. This highlights the need for algorithms capable of applying info ... Full text Cite

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 Robustness of Hyperbolic Neural Networks by Lipschitz Analysis

Conference Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · August 24, 2024 Hyperbolic neural networks (HNNs) are emerging as a promising tool for representing data embedded in non-Euclidean geometries, yet their adoption has been hindered by challenges related to stability and robustness. In this work, we conduct a rigorous Lipsc ... Full text Cite

TopoUT: Enhancing Cell Segmentation Through Efficient Topological Regularization

Conference Proceedings International Symposium on Biomedical Imaging · January 1, 2024 Cell segmentation plays a crucial role in biological image analysis, serving as a fundamental step with downstream applications in pathology, clinical diagnosis, and drug discovery. Recent advancements in deep learning, especially the Unet architecture, ha ... Full text Cite

Hyperbolic Kernel Convolution: A Generic Framework

Conference Proceedings of Machine Learning Research · January 1, 2024 The past sexennium has witnessed rapid advancements of hyperbolic neural networks. However, it is challenging to learn good hyperbolic representations since common Euclidean neural operations, such as convolution, do not extend to the hyperbolic space. Mos ... Cite

Enhancing Node-Level Adversarial Defenses by Lipschitz Regularization of Graph Neural Networks

Conference Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · August 4, 2023 Graph neural networks (GNNs) have shown considerable promise for graph-structured data. However, they are also known to be unstable and vulnerable to perturbations and attacks. Recently, the Lipschitz constant has been adopted as a control on the stability ... Full text Cite

An Unpooling Layer for Graph Generation

Conference Proceedings of Machine Learning Research · April 25, 2023 Link to item Cite

Robust Variational Autoencoding with Wasserstein Penalty for Novelty Detection

Conference Proceedings of Machine Learning Research · April 25, 2023 Link to item Cite

Robust Subspace Recovery Layer for Unsupervised Anomaly Detection

Conference · May 1, 2020 We propose a neural network for unsupervised anomaly detection with a novel robust subspace recovery layer (RSR layer). This layer seeks to extract the underlying subspace from a latent representation of the given data and removes outliers that lie away fr ... Link to item Cite

Encoding robust representation for graph generation

Conference Proceedings of the International Joint Conference on Neural Networks · July 1, 2019 Generative networks have made it possible to generate meaningful signals such as images and texts from simple noise. Recently, generative methods based on GAN and VAE were developed for graphs and graph signals. However, the mathematical properties of thes ... Full text Cite

Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks

Conference Proceedings of Machine Learning Research Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks. Despite advancements of methodology based on deep learning in recent years, existing benchmarking approaches exhibit limitations that hinder a comprehensive ... Link to item Cite