Dongmian Zou

Journal article SIAM Journal on Mathematics of Data Science · January 1, 2025 Generative adversarial networks are popular for generative tasks; however‚ they often require careful architecture selection and extensive empirical tuning‚ and they are prone to mode collapse. To overcome these challenges‚ we propose a novel model that id ... Full text Cite

Recognition of Yuan blue and white porcelain produced in Jingdezhen based on graph anomaly detection combining portable X-ray fluorescence spectrometry

Journal article Heritage Science · December 1, 2024 The blue and white porcelain produced in Jingdezhen during China’s Yuan Dynasty is an outstanding cultural heritage of ceramic art that has attracted wide attention for its identification. However, the traditional visual identification method is susceptibl ... Full text Cite

Graph Neural Network-Based Node Deployment for Throughput Enhancement.

Journal article IEEE transactions on neural networks and learning systems · October 2024 The recent rapid growth in mobile data traffic entails a pressing demand for improving the throughput of the underlying wireless communication networks. Network node deployment has been considered as an effective approach for throughput enhancement which, ... Full text Cite

GRAM: An interpretable approach for graph anomaly detection using gradient attention maps.

Journal article Neural networks : the official journal of the International Neural Network Society · October 2024 Detecting unusual patterns in graph data is a crucial task in data mining. However, existing methods face challenges in consistently achieving satisfactory performance and often lack interpretability, which hinders our understanding of anomaly detection de ... Full text Cite

Translating Test Responses to Images for Test-termination Prediction via Multiple Machine Learning Strategies

Journal article ACM Transactions on Design Automation of Electronic Systems · August 13, 2024 Failure diagnosis is a software-based, data-driven procedure. Collecting an excessive amount of fail data not only increases the overall test cost but can also potentially reduce diagnostic resolution. Thus, test-termination prediction is proposed to dynam ... Full text Cite

GRAND: A Graph Neural Network Framework for Improved Diagnosis

Journal article IEEE Transactions on Computer Aided Design of Integrated Circuits and Systems · April 1, 2024 The pursuit of accurate diagnosis with good resolution is driven by yield learning during both early bring-up and production excursions. Unfortunately, fault callouts from diagnosis tools often render poor resolution that hinders the follow-up failure anal ... Full text Cite

Autoencoding Hyperbolic Representation for Adversarial Generation

Journal article Transactions on Machine Learning Research · January 1, 2024 With the recent advance of geometric deep learning, neural networks have been extensively used for data in non-Euclidean domains. In particular, hyperbolic neural networks have proved successful in processing hierarchical information of data. However, many ... Cite

Interpretability-Aware Industrial Anomaly Detection Using Autoencoders

Journal article IEEE Access · January 1, 2023 The past decade has witnessed wide applications of deep neural networks in anomaly detection. However, the dearth of interpretability in neural networks often hinders their reliability, especially for industrial applications where practical users heavily r ... Full text Cite

Ensemble Riemannian data assimilation over the Wasserstein space

Journal article Nonlinear Processes in Geophysics · July 6, 2021 In this paper, we present an ensemble data assimilation paradigm over a Riemannian manifold equipped with the Wasserstein metric. Unlike the Euclidean distance used in classic data assimilation methodologies, the Wasserstein metric can capture the translat ... Full text Cite

Graph convolutional neural networks via scattering

Journal article Applied and Computational Harmonic Analysis · November 1, 2020 We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs. We show that under certain conditions, any feature generated by such a network is approximately invariant to permutations and stable to si ... Full text Cite

Regularized variational data assimilation for bias treatment using the Wasserstein metric

Journal article Quarterly Journal of the Royal Meteorological Society · July 1, 2020 This article presents a new variational data assimilation (VDA) approach for the formal treatment of bias in both model outputs and observations. This approach relies on the Wasserstein metric, stemming from the theory of optimal mass transport, to penaliz ... Full text Open Access Cite

On Lipschitz Bounds of General Convolutional Neural Networks

Journal article IEEE Transactions on Information Theory · March 1, 2020 Many convolutional neural networks (CNN's) have a feed-forward structure. In this paper, we model a general framework for analyzing the Lipschitz bounds of CNN's and propose a linear program that estimates these bounds. Several CNN's, including the scatter ... Full text Cite

On Lipschitz analysis and Lipschitz synthesis for the phase retrieval problem

Journal article Linear Algebra and Its Applications · May 1, 2016 We prove two results with regard to reconstruction from magnitudes of frame coefficients (the so called "phase retrieval problem"). First we show that phase retrievable nonlinear maps are bi-Lipschitz with respect to appropriate metrics on the quotient spa ... Full text Open Access Cite