Zhanxing Zhu

Publications101
h-index22
Citations2,454
Highly Influential Citations301
Claim Author Page
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Yoshua Bengio
  • 836 Publications • 326,576 Citations
  • I. Goodfellow
  • 117 Publications • 114,309 Citations
  • Quoc V. Le
  • 212 Publications • 87,254 Citations
  • Nicolas Papernot
  • 94 Publications • 16,001 Citations
  • Publications
  • Influence
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
TLDR
This paper proposes a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain, and builds the model with complete convolutional structures, which enable much faster training speed with fewer parameters. Expand
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
TLDR
It is shown that adversarial training can be cast as a discrete time differential game, and the proposed algorithm YOPO (You Only Propagate Once) can achieve comparable defense accuracy with approximately 1/5 ~ 1/4 GPU time of the projected gradient descent (PGD) algorithm. Expand
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
TLDR
This work studies a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics, and shows that the anisotropic noise in SGD helps to escape from sharp and poor minima effectively, towards more stable and flat minima that typically generalize well. Expand
Multi-Stage Self-Supervised Learning for Graph Convolutional Networks
TLDR
A novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised (M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Expand
Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting
You Only Propagate Once: Painless Adversarial Training Using Maximal Principle
TLDR
This work fully exploits structure of deep neural networks and proposes a novel strategy to decouple the adversary update with the gradient back propagation, which avoids forward and backward propagating the data too many times in one iteration, and restricts core descent directions computation to the first layer of the network, thus speeding up every iteration significantly. Expand
Reinforced Continual Learning
TLDR
A novel approach for continual learning is proposed, which searches for the best neural architecture for each coming task via sophisticatedly designed reinforcement learning strategies, and which outperforms existing continual learning alternatives for deep networks. Expand
Covariance-Controlled Adaptive Langevin Thermostat for Large-Scale Bayesian Sampling
TLDR
This article proposes a covariance-controlled adaptive Langevin thermostat that can effectively dissipate parameter-dependent noise while maintaining a desired target distribution and achieves a substantial speedup over popular alternative schemes for large-scale machine learning applications. Expand
Interpreting Adversarially Trained Convolutional Neural Networks
TLDR
Surprisingly, it is found that adversarial training alleviates the texture bias of standard CNNs when trained on object recognition tasks, and helps CNNs learn a more shape-biased representation. Expand
Understanding and Enhancing the Transferability of Adversarial Examples
TLDR
This work systematically study how two classes of factors that might influence the transferability of adversarial examples are influenced, including model-specific factors, including network architecture, model capacity and test accuracy, and the local smoothness of loss function for constructing adversarial example. Expand
...
1
2
3
4
5
...