Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Zhanxing Zhu

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


Mar 31, 2021
Zeke Xie, Li Yuan, Zhanxing Zhu, Masashi Sugiyama

* 19 pages, 12 figures 

  Access Paper or Ask Questions

Amata: An Annealing Mechanism for Adversarial Training Acceleration


Dec 15, 2020
Nanyang Ye, Qianxiao Li, Xiao-Yun Zhou, Zhanxing Zhu

* accepted by AAAI 

  Access Paper or Ask Questions

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


Oct 20, 2020
Guangda Ji, Zhanxing Zhu


  Access Paper or Ask Questions

Neural Approximate Sufficient Statistics for Implicit Models


Oct 20, 2020
Yanzhi Chen, Dinghuai Zhang, Michael Gutmann, Aaron Courville, Zhanxing Zhu


  Access Paper or Ask Questions

Automatic Data Augmentation for 3D Medical Image Segmentation


Oct 07, 2020
Ju Xu, Mengzhang Li, Zhanxing Zhu

* 10 pages 

  Access Paper or Ask Questions

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


Aug 10, 2020
Baifeng Shi, Dinghuai Zhang, Qi Dai, Zhanxing Zhu, Yadong Mu, Jingdong Wang

* Accepted to ICML2020. Code is available at https://github.com/bfshi/InfoDrop 

  Access Paper or Ask Questions

Spherical Motion Dynamics of Deep Neural Networks with Batch Normalization and Weight Decay


Jul 02, 2020
Ruosi Wan, Zhanxing Zhu, Xiangyu Zhang, Jian Sun


  Access Paper or Ask Questions

Classify and Generate Reciprocally: Simultaneous Positive-Unlabelled Learning and Conditional Generation with Extra Data


Jun 14, 2020
Bing Yu, Ke Sun, He Wang, Zhouchen Lin, Zhanxing Zhu


  Access Paper or Ask Questions

Global Robustness Verification Networks


Jun 08, 2020
Weidi Sun, Yuteng Lu, Xiyue Zhang, Zhanxing Zhu, Meng Sun


  Access Paper or Ask Questions

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


Feb 21, 2020
Dinghuai Zhang, Mao Ye, Chengyue Gong, Zhanxing Zhu, Qiang Liu


  Access Paper or Ask Questions

Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy


Nov 21, 2019
Ke Sun, Bing Yu, Zhouchen Lin, Zhanxing Zhu


  Access Paper or Ask Questions

Towards Making Deep Transfer Learning Never Hurt


Nov 18, 2019
Ruosi Wan, Haoyi Xiong, Xingjian Li, Zhanxing Zhu, Jun Huan

* accapted as long paper at the 19th IEEE International Conference on Data Mining, 2019 
* 10 pages 

  Access Paper or Ask Questions

Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling


Aug 20, 2019
He Wang, Edmond S. L. Ho, Hubert P. H. Shum, Zhanxing Zhu

* IEEE Transaction on Visualization and Computer Graphics, 2019 
* 12 pages, Accepted in IEEE Transaction on Visualization and Computer Graphics 

  Access Paper or Ask Questions

AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models


Aug 14, 2019
Ke Sun, Zhouchen Lin, Zhanxing Zhu


  Access Paper or Ask Questions

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


Jun 18, 2019
Jingfeng Wu, Wenqing Hu, Haoyi Xiong, Jun Huan, Zhanxing Zhu


  Access Paper or Ask Questions

Differentiable Neural Architecture Search via Proximal Iterations


May 30, 2019
Quanming Yao, Ju Xu, Wei-Wei Tu, Zhanxing Zhu


  Access Paper or Ask Questions

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


May 24, 2019
Bing Yu, Junzhao Zhang, Zhanxing Zhu


  Access Paper or Ask Questions

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle


May 23, 2019
Dinghuai Zhang, Tianyuan Zhang, Yiping Lu, Zhanxing Zhu, Bin Dong


  Access Paper or Ask Questions

Interpreting Adversarially Trained Convolutional Neural Networks


May 23, 2019
Tianyuan Zhang, Zhanxing Zhu

* To apper in ICML19 

  Access Paper or Ask Questions

Bayesian Optimized Continual Learning with Attention Mechanism


May 10, 2019
Ju Xu, Jin Ma, Zhanxing Zhu

* 8 pages 

  Access Paper or Ask Questions

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


Mar 13, 2019
Bing Yu, Haoteng Yin, Zhanxing Zhu


  Access Paper or Ask Questions

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


Mar 03, 2019
Bing Yu, Mengzhang Li, Jiyong Zhang, Zhanxing Zhu


  Access Paper or Ask Questions

Virtual Adversarial Training on Graph Convolutional Networks in Node Classification


Feb 28, 2019
Ke Sun, Hantao Guo, Zhanxing Zhu, Zhouchen Lin


  Access Paper or Ask Questions

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks


Feb 28, 2019
Ke Sun, Zhanxing Zhu, Zhouchen Lin


  Access Paper or Ask Questions

Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN


Feb 28, 2019
Ke Sun, Zhanxing Zhu, Zhouchen Lin


  Access Paper or Ask Questions

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


Feb 28, 2019
Ke Sun, Zhanxing Zhu, Zhouchen Lin


  Access Paper or Ask Questions

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


Jan 18, 2019
Wenqing Hu, Zhanxing Zhu, Haoyi Xiong, Jun Huan

* first and preliminary version 

  Access Paper or Ask Questions

Tangent-Normal Adversarial Regularization for Semi-supervised Learning


Aug 18, 2018
Bing Yu, Jingfeng Wu, Zhanxing Zhu


  Access Paper or Ask Questions