Z
Zhanxing Zhu
Researcher at Peking University
Publications - 105
Citations - 5476
Zhanxing Zhu is an academic researcher from Peking University. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 26, co-authored 99 publications receiving 2925 citations. Previous affiliations of Zhanxing Zhu include Aalto University & University of Edinburgh.
Papers
More filters
Proceedings ArticleDOI
Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting
Bing Yu,Haoteng Yin,Zhanxing Zhu +2 more
TL;DR: Wang et al. as mentioned in this paper proposed a novel deep learning framework, Spatio-Temporal Graph Convolutional Networks (STGCN), to tackle the time series prediction problem in traffic domain.
Proceedings Article
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
TL;DR: 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.
Posted Content
Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting
Mengzhang Li,Zhanxing Zhu +1 more
TL;DR: The proposed Spatial-Temporal Fusion Graph Neural Networks (STFGNN) could effectively learn hidden spatial-temporal dependencies by a novel fusion operation of various spatial and temporal graphs, which is generated by a data-driven method.
Posted Content
Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes
Lei Wu,Zhanxing Zhu,Weinan E +2 more
TL;DR: The underlying reasons why deep neural networks often generalize well are investigated, and it is shown that the characteristics the landscape of the loss function that explains the good generalization capability is the volume of basin of attraction of good minima.
Proceedings Article
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects.
TL;DR: 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.