Zhanxing Zhu

G. Barreto, Zhanxing Zhu, F. Corona, 2013, 2013 BRICS Congress on Computational Intelligence and 11th Brazilian Congress on Computational Intelligence.

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks

Zhouchen Lin, Zhanxing Zhu, Ke Sun, 2019, AAAI.

Adaptive Progressive Continual Learning

Zhanxing Zhu, Ju Xu, Jin Ma, 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

GrOD: Deep Learning with Gradients Orthogonal Decomposition for Knowledge Transfer, Distillation, and Adversarial Training

Zhanxing Zhu, Ruosi Wan, Haoyi Xiong, 2022, ACM Trans. Knowl. Discov. Data.

Neural Information Processing Systems (NIPS)

Zhanxing Zhu, Amos Storkey, Benedict Leimkuhler, 2015 .

Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization

Masashi Sugiyama, M. Sugiyama, Zeke Xie, 2021, ICML.

Filling the Soap Bubbles: Efficient Black-Box Adversarial Certification with Non-Gaussian Smoothing

Qiang Liu, Zhanxing Zhu, Mao Ye, 2019 .

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

Zhanxing Zhu, Bing Yu, Haoteng Yin, 2017, IJCAI.

Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning

Jianhong Wang, Zhanxing Zhu, Yaodong Yang, 2017, NeurIPS.

Neural Approximate Sufficient Statistics for Implicit Models pdf

Zhanxing Zhu, Aaron C. Courville, Aaron Courville, 2020, ICLR.

On the Noisy Gradient Descent that Generalizes as SGD

Zhanxing Zhu, Vladimir Braverman, Haoyi Xiong, 2019, ICML.

The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects

Zhanxing Zhu, Jinwen Ma, Bing Yu, 2018, ICML.

Quadratic Form Innovation to Blind Source Separation

Zhiguo Jiang, Zhanxing Zhu, Zhenwei Shi, 2009, 2009 Fifth International Conference on Natural Computation.

A Fixed-Point Algorithm for Nonnegative Independent Component Analysis

Zhiguo Jiang, Zhanxing Zhu, Zhenwei Shi, 2009, 2009 Fifth International Conference on Natural Computation.

AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models pdf

Zhanxing Zhu, Ke Sun, Zhouchen Lin, 2019, ICLR.

Virtual Adversarial Training on Graph Convolutional Networks in Node Classification pdf

Zhanxing Zhu, Ke Sun, Zhouchen Lin, 2019, PRCV.

An Annealing Mechanism for Adversarial Training Acceleration

Zhanxing Zhu, Nanyang Ye, Xiao-Yun Zhou, 2021, IEEE Transactions on Neural Networks and Learning Systems.

On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks pdf

Zhanxing Zhu, Bing Yu, Junzhao Zhang, 2019, ArXiv.

You Only Propagate Once: Painless Adversarial Training Using Maximal Principle

Bin Dong, Zhanxing Zhu, Yiping Lu, 2019 .

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle pdf

Bin Dong, Zhanxing Zhu, Yiping Lu, 2019, NeurIPS.

Fine-grained differentiable physics: a yarn-level model for fabrics

Zhanxing Zhu, A. Bulpitt, He Wang, 2022, ICLR.

Interpreting Adversarially Trained Convolutional Neural Networks

Zhanxing Zhu, Tianyuan Zhang, Zhanxing Zhu, 2019, ICML.

Yet Another Text Captcha Solver: A Generative Adversarial Network Based Approach

Zheng Wang, Yansong Feng, Zhanxing Zhu, 2018, CCS.

Understanding and Enhancing the Transferability of Adversarial Examples pdf

Lei Wu, Zhanxing Zhu, E Weinan, 2018, ArXiv.

3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting pdf

Zhanxing Zhu, Bing Yu, Jiyong Zhang, 2019, ArXiv.

Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting

Li Mengzhang, Zhu Zhanxing, Zhanxing Zhu, 2020, AAAI.

SIPID: A deep learning framework for sinogram interpolation and image denoising in low-dose CT reconstruction

Zhanxing Zhu, Huizhuo Yuan, Jinzhu Jia, 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

Automatic Data Augmentation for 3D Medical Image Segmentation pdf

Zhanxing Zhu, Mengzhang Li, Ju Xu, 2020, MICCAI.

Adversarial Invariant Learning

Zhanxing Zhu, Guang-Zhong Yang, Zhenguo Li, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Adversarial attacks on Faster R-CNN object detector

Zhanxing Zhu, Kunfeng Wang, Yutong Wang, 2020, Neurocomputing.

Sampling Sparse Representations with Randomized Measurement Langevin Dynamics

Zhanxing Zhu, Haoyi Xiong, Dejing Dou, 2021, ACM Trans. Knowl. Discov. Data.

Towards Understanding and Improving the Transferability of Adversarial Examples in Deep Neural Networks

Zhanxing Zhu, Lei Wu, Lei Wu, 2020, ACML.

Differentiable Neural Architecture Search via Proximal Iterations pdf

Zhanxing Zhu, Quanming Yao, Wei-Wei Tu, 2019, ArXiv.

Novel subgroups of patients with adult-onset diabetes in Chinese and US populations.

Zhanxing Zhu, L. Ji, Xianghai Zhou, 2019, The lancet. Diabetes & endocrinology.

Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework pdf

Qiang Liu, Zhanxing Zhu, Mao Ye, 2020, NeurIPS.

Spherical Motion Dynamics: Learning Dynamics of Neural Network with Normalization, Weight Decay, and SGD

Jian Sun, Ruosi Wan, Zhanxing Zhu, 2020 .

The Regularization Effects of Anisotropic Noise in Stochastic Gradient Descent pdf

Lei Wu, Zhanxing Zhu, Jinwen Ma, 2018, ArXiv.

Bayesian Adversarial Learning

Zhanxing Zhu, Nanyang Ye, Zhanxing Zhu, 2018, NeurIPS.

Stochastic Fractional Hamiltonian Monte Carlo

Zhanxing Zhu, Nanyang Ye, Zhanxing Zhu, 2018, IJCAI.

Langevin Dynamics with Continuous Tempering for High-dimensional Non-convex Optimization pdf

Zhanxing Zhu, Rafal Mantiuk, Nanyang Ye, 2017, ArXiv.

Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks

Zhanxing Zhu, Rafal Mantiuk, Nanyang Ye, 2017, NIPS.

Efficient Neural Architecture Search via Proximal Iterations

Wei-Wei Tu, Zhanxing Zhu, Quanming Yao, 2019, AAAI.

Amata: An Annealing Mechanism for Adversarial Training Acceleration pdf

Zhanxing Zhu, Nanyang Ye, Qianxiao Li, 2019, AAAI.

Spatio-Temporal Manifold Learning for Human Motions via Long-Horizon Modeling

Zhanxing Zhu, Hubert P. H. Shum, Edmond S. L. Ho, 2019, IEEE Transactions on Visualization and Computer Graphics.

Implicit Bias of Adversarial Training for Deep Neural Networks

Zhanxing Zhu, Bochen Lv, 2022, ICLR.

Tangent-Normal Adversarial Regularization for Semi-Supervised Learning

Zhanxing Zhu, Bing Yu, Jingfeng Wu, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

MonoFlow: Rethinking Divergence GANs via the Perspective of Differential Equations

Zhanxing Zhu, Mingxuan Yi, Song Liu, 2023, ArXiv.

ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling pdf

Zhanxing Zhu, Bing Yu, Haoteng Yin, 2019, ArXiv.

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

Haoteng Yin, Zhanxing Zhu, Ting Yu, 2017, IJCAI.

Towards Making Deep Transfer Learning Never Hurt

Zhanxing Zhu, Haoyi Xiong, Xingjian Li, 2019, 2019 IEEE International Conference on Data Mining (ICDM).

Bayesian Optimized Continual Learning with Attention Mechanism pdf

Zhanxing Zhu, Ju Xu, Jin Ma, 2019, ArXiv.

Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher pdf

Zhanxing Zhu, Guangda Ji, Zhanxing Zhu, 2020, NeurIPS.

Appendix: Spherical Motion Dynamics

Jian Sun, X. Zhang, Zhanxing Zhu, 2022 .

Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes

Lei Wu, E. Weinan, Zhanxing Zhu, 2017, ArXiv.

Towards Understanding Adversarial Examples Systematically: Exploring Data Size, Task and Model Factors pdf

Zhanxing Zhu, Ke Sun, Zhouchen Lin, 2019, ArXiv.

SpHMC: Spectral Hamiltonian Monte Carlo

Zhanxing Zhu, Haoyi Xiong, Cheng-Zhong Xu, 2019, AAAI.

Integrating local information for inference and optimization in machine learning

Zhanxing Zhu, Zhanxing Zhu, 2016 .

Aggregation Under Bias: Rényi Divergence Aggregation and Its Implementation via Machine Learning Markets

Zhanxing Zhu, Amos J. Storkey, Jinli Hu, 2015, ECML/PKDD.

Using Generative Adversarial Networks to Break and Protect Text Captchas

Yansong Feng, Dingyi Fang, Xiaojiang Chen, 2020, ACM Trans. Priv. Secur..

Hyperspectral unmixing using non-negative matrix factorization with automatically estimating regularization parameters

Zhiguo Jiang, Zhanxing Zhu, Zhenwei Shi, 2011, 2011 Seventh International Conference on Natural Computation.

Neural Control Variates for Monte Carlo Variance Reduction

Zhanxing Zhu, Haoyi Xiong, Mingjun Zhong, 2019, ECML/PKDD.

MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flows

Zhanxing Zhu, Mingxuan Yi, Song Liu, 2023, ICML.

Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting

Haoteng Yin, Zhanxing Zhu, Ting Yu, 2017, IJCAI.

Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability

D. Dou, Zhanxing Zhu, Dongrui Wu, 2023, arXiv.org.

Quasi-potential as an implicit regularizer for the loss function in the stochastic gradient descent pdf

Zhanxing Zhu, Haoyi Xiong, Wenqing Hu, 2019, ArXiv.

Neural Control Variates for Variance Reduction pdf

Zhanxing Zhu, Mingjun Zhong, Ruosi Wan, 2018, ArXiv.

Multiplicative Updates for Learning with Stochastic Matrices

Erkki Oja, Zhanxing Zhu, Zhirong Yang, 2013, SCIA.

Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI pdf

Quanshi Zhang, Zhanxing Zhu, Tian Han, 2021, ArXiv.

Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN pdf

Zhanxing Zhu, Ke Sun, Zhouchen Lin, 2019, ArXiv.

Simplifying Graph Attention Networks with Source-Target Separation

Yansong Feng, Zhanxing Zhu, Rui Yan, 2020, ECAI.

Automatic Rank Determination in Projective Nonnegative Matrix Factorization

Erkki Oja, Zhanxing Zhu, Zhirong Yang, 2010, LVA/ICA.

The Multiplicative Noise in Stochastic Gradient Descent: Data-Dependent Regularization, Continuous and Discrete Approximation pdf

Zhanxing Zhu, Haoyi Xiong, Wenqing Hu, 2019, ArXiv.

Adaptive Stochastic Primal-Dual Coordinate Descent for Separable Saddle Point Problems

Zhanxing Zhu, Amos J. Storkey, A. Storkey, 2015, ECML/PKDD.

On the Noisy Gradient Descent that Generalizes as SGD

Wenqing Hu, V. Braverman, Zhanxing Zhu, 2019, ICML.

The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Minima and Regularization Effects

Lei Wu, Zhanxing Zhu, Ting Yu, 2018, 1803.00195.

Informative Dropout for Robust Representation Learning: A Shape-bias Perspective

Yadong Mu, Zhanxing Zhu, Jingdong Wang, 2020, ICML.