publications

2024

1. AI Journal

   Functional Relation Field: A Model-Agnostic Framework for Multivariate Time Series Forecasting

   Ting Li ,  Bing Yu ,  Jianguo Li ,  and  Zhanxing Zhu

   Artificial Intelligence, 2024

   Abs PDF

   In multivariate time series forecasting, the most popular strategy for modeling the relationship between multiple time series is the construction of graph, where each time series is represented as a node and related nodes are connected by edges. However, the relationship between multiple time series is typically complicated, e.g. the sum of outflows from upstream nodes may be equal to the inflows of downstream nodes. Such relations widely exist in many real-world scenarios for multivariate time series forecasting, yet are far from well studied. In these cases, graph might be insufficient for modeling the complex dependency between nodes. To this end, we explore a new framework to model the inter-node relationship in a more precise way based our proposed inductive bias, Functional Relation Field, where a group of functions parameterized by neural networks are learned to characterize the dependency between multiple time series. Essentially, these learned functions then form a “field”, i.e. a particular set of constraints, to regularize the training loss of the backbone prediction network and enforce the inference process to satisfy these constraints. Since our framework introduces the relationship bias in a data-driven manner, it is flexible and model-agnostic such that it can be applied to any existing multivariate time series prediction networks for boosting performance. The experiment is conducted on one toy dataset to show our approach can well recover the true constraint relationship between nodes. And various real-world datasets are also considered with different backbone prediction networks. Results show that the prediction error can be reduced remarkably with the aid of the proposed framework.

2023

1. ICML

   MonoFlow: Rethinking Divergence GANs via the Perspective of Differential Equations

   Mingxuan Yi ,  Zhanxing Zhu ,  and  Song Liu

   In International Conference for Machine Learning (ICML) , 2023

   PDF
2. NeurIPS

   Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling

   Ting Li ,  Jianguo Li ,  and  Zhanxing Zhu

   In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS) , 2023

   PDF
3. NeurIPS

   Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network

   Bochen Lyu ,  and  Zhanxing Zhu

   In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS) , 2023

   PDF
4. MLST

   Stochastic Gradient Descent with Random Label Noises: Doubly Stochastic Models and Inference Stabilizer

   Haoyi Xiong ,  Xuhong Li ,  Boyang Yu ,  Dongrui Wu ,  Zhanxing Zhu ,  and  Dejing Dou

   Machine Learning: Science and Technology, 2023

   PDF
5. ACML

   Patch-level neighborhood interpolation: A general and effective graph-based regularization strategy

   Ke Sun ,  Bing Yu ,  Zhouchen Lin ,  and  Zhanxing Zhu

   In Asian Conference on Machine Learning (ACML) , 2023

2022

1. ICLR

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

   Deshan Gong ,  Zhanxing Zhu ,  Andrew J Bulpitt ,  and  He Wang

   In International Conference on Learning Representation (ICLR) , 2022
2. ICLR

   Implicit Bias of Adversarial Training for Deep Neural Networks

   Bochen Lv ,  and  Zhanxing Zhu

   In International Conference on Learning Representation (ICLR) , 2022

   PDF
3. TKDD

   Grod: Deep learning with gradients orthogonal decomposition for knowledge transfer, distillation, and adversarial training

   Haoyi Xiong ,  Ruosi Wan ,  Jian Zhao ,  Zeyu Chen ,  Xingjian Li ,  Zhanxing Zhu , and 1 more author

   ACM Transactions on Knowledge Discovery from Data, 2022

2021

1. TVCG

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

   He Wang ,  Edmond S. L. Ho ,  Hubert P. H. Shum ,  and  Zhanxing Zhu

   IEEE Transactions on Visualization and Computer Graphics, 2021
2. TKDD

   Sampling sparse representations with randomized measurement langevin dynamics

   Kafeng Wang ,  Haoyi Xiong ,  Jiang Bian ,  Zhanxing Zhu ,  Qian Gao ,  Zhishan Guo , and 3 more authors

   ACM Transactions on Knowledge Discovery from Data (TKDD), 2021
3. ICML

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

   Zeke Xie ,  Li Yuan ,  Zhanxing Zhu ,  and  Masashi Sugiyama

   In International Conference for Machine Learning (ICML) , 2021
4. ICLR

   AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models

   Ke Sun ,  Zhanxing Zhu ,  and  Zhouchen Lin

   In International Conference on Learning Representation (ICLR) , 2021
5. CVPR

   Adversarial invariant learning

   Nanyang Ye ,  Jingxuan Tang ,  Huayu Deng ,  Xiao-Yun Zhou ,  Qianxiao Li ,  Zhenguo Li , and 2 more authors

   In 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2021
6. TPAMI

   Adaptive progressive continual learning

   Ju Xu ,  Jin Ma ,  Xuesong Gao ,  and  Zhanxing Zhu

   IEEE transactions on pattern analysis and machine intelligence (TPAMI), 2021
7. TNNLS

   An annealing mechanism for adversarial training acceleration

   Nanyang Ye ,  Qianxiao Li ,  Xiao-Yun Zhou ,  and  Zhanxing Zhu

   IEEE Transactions on Neural Networks and Learning Systems, 2021
8. NeurIPS

   Spherical motion dynamics: Learning dynamics of normalized neural network using sgd and weight decay

   Ruosi Wan ,  Zhanxing Zhu ,  Xiangyu Zhang ,  and  Jian Sun

   Advances in Neural Information Processing Systems (NeurIPS), 2021

   PDF

2020

1. IJCNN

   Learning to search efficient densenet with layer-wise pruning

   Xuanyang Zhang ,  Hao Liu ,  Zhanxing Zhu ,  and  Zenglin Xu

   In 2020 International Joint Conference on Neural Networks (IJCNN) , 2020
2. ECML

   Neural control variates for Monte Carlo variance reduction

   Ruosi Wan ,  Mingjun Zhong ,  Haoyi Xiong ,  and  Zhanxing Zhu

   In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2019, Würzburg, Germany, September 16–20, 2019, Proceedings, Part II , 2020
3. AAAI

   Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes.

   Ke Sun ,  Zhouchen Lin ,  and  Zhanxing Zhu

   In AAAI , 2020
4. AAAI

   Efficient Neural Architecture Search via Proximal Iterations.

   Quanming Yao ,  Ju Xu ,  Wei-Wei Tu ,  and  Zhanxing Zhu

   In AAAI , 2020
5. TOPS

   Using generative adversarial networks to break and protect text captchas

   Guixin Ye ,  Zhanyong Tang ,  Dingyi Fang ,  Zhanxing Zhu ,  Yansong Feng ,  Pengfei Xu , and 3 more authors

   ACM Transactions on Privacy and Security (TOPS), 2020
6. ICML

   On the Noisy Gradient Descent that Generalizes as SGD

   Jingfeng Wu ,  Wenqing Hu ,  Haoyi Xiong ,  Jun Huan ,  Vladimir Braverman ,  and  Zhanxing Zhu

   In International Conference for Machine Learning (ICML) , 2020
7. AAAI

   Amata: An Annealing Mechanism for Adversarial Training Acceleration

   Nanyang Ye ,  Qianxiao Li ,  Xiao-Yun Zhou ,  and  Zhanxing Zhu

   In AAAI , 2020
8. ECAI

   Simplifying Graph Attention Networks with Source-Target Separation

   Hantao Guo ,  Rui Yan ,  Yansong Feng ,  Xuesong Gao ,  and  Zhanxing Zhu

   In ECAI , 2020
9. NeurIPS

   Black-box certification with randomized smoothing: A functional optimization based framework

   Dinghuai Zhang ,  Mao Ye ,  Chengyue Gong ,  Zhanxing Zhu ,  and  Qiang Liu

   In NeurIPS , 2020
10. ICML

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

    Baifeng Shi ,  Dinghuai Zhang ,  Qi Dai ,  Zhanxing Zhu ,  Yadong Mu ,  and  Jingdong Wang

    In International Conference for Machine Learning (ICML) , 2020
11. MICCAI

    Automatic data augmentation for 3D medical image segmentation

    Ju Xu ,  Mengzhang Li ,  and  Zhanxing Zhu

    In Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part I 23 , 2020
12. ACML

    Towards understanding and improving the transferability of adversarial examples in deep neural networks

    Lei Wu ,  and  Zhanxing Zhu

    In Asian Conference on Machine Learning (ACML) , 2020
13. ICLR

    Neural Approximate Sufficient Statistics for Implicit Models

    Yanzhi Chen ,  Dinghuai Zhang ,  Michael Gutmann ,  Aaron Courville ,  and  Zhanxing Zhu

    In International Conference on Learning Representation (ICLR) , 2020
14. NeurIPS

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

    Guangda Ji ,  and  Zhanxing Zhu

    In Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS) , 2020

    PDF
15. ICML

    On breaking deep generative model-based defenses and beyond

    Yanzhi Chen ,  Renjie Xie ,  and  Zhanxing Zhu

    In International Conference on Machine Learning (ICML) , 2020
16. AAAI

    Spatial-temporal fusion graph neural networks for traffic flow forecasting

    Mengzhang Li ,  and  Zhanxing Zhu

    In AAAI Conference on Artificial Intelligence , 2020

2019

1. CVPR

   Tangent-Normal Adversarial Regularization for Semi-supervised Learning

   Bing Yu ,  Jingfeng Wu ,  and  Zhanxing Zhu

   In CVPR , 2019
2. AAAI

   SpHMC: Spectral Hamiltonian Monte Carlo

   Haoyi Xiong ,  Kafeng Wang ,  Jiang Bian ,  Zhanxing Zhu ,  Cheng-Zhong Xu ,  Zhishan Guo , and 1 more author

   In AAAI 2019 , 2019
3. Lancet

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

   Xiantong Zou ,  Xianghai Zhou ,  Zhanxing Zhu ,  and  Linong Ji

   The Lancet Diabetes & Endocrinology, 2019
4. PRCV

   Virtual adversarial training on graph convolutional networks in node classification

   Ke Sun ,  Zhouchen Lin ,  Hantao Guo ,  and  Zhanxing Zhu

   In Pattern Recognition and Computer Vision: Second Chinese Conference, PRCV 2019, Xi’an, China, November 8–11, 2019, Proceedings, Part I 2 , 2019
5. 3D graph convolutional networks with temporal graphs: A spatial information free framework for traffic forecasting

   Bing Yu ,  Mengzhang Li ,  Jiyong Zhang ,  and  Zhanxing Zhu

   arXiv preprint arXiv:1903.00919, 2019
6. ST-UNet: A spatio-temporal U-network for graph-structured time series modeling

   Bing Yu ,  Haoteng Yin ,  and  Zhanxing Zhu

   arXiv preprint arXiv:1903.05631, 2019
7. NeurIPS

   You only propagate once: Accelerating adversarial training via maximal principle

   Dinghuai Zhang ,  Tianyuan Zhang ,  Yiping Lu ,  Zhanxing Zhu ,  and  Bin Dong

   In Advances in Neural Information Processing Systems (NeurIPS) , 2019

   PDF
8. ICML

   Interpreting Adversarially Trained Convolutional Neural Networks

   Tianyuan Zhang ,  and  Zhanxing Zhu

   In International Conference on Machine Learning (ICML) , 2019
9. ICML

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

   Zhanxing Zhu ,  Jingfeng Wu ,  Bing Yu ,  Lei Wu ,  and  Jinwen Ma

   In International Conference on Machine Learning (ICML) , 2019

   PDF
10. NLPCC

    How question generation can help question answering over knowledge base

    Sen Hu ,  Lei Zou ,  and  Zhanxing Zhu

    In Natural Language Processing and Chinese Computing: 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9–14, 2019, Proceedings, Part I 8 , 2019
11. ICDM

    Towards making deep transfer learning never hurt

    Ruosi Wan ,  Haoyi Xiong ,  Xingjian Li ,  Zhanxing Zhu ,  and  Jun Huan

    In 2019 IEEE International Conference on Data Mining (ICDM) , 2019

2018

1. IJCAI

   Spatio-temporal graph convolutional neural network: A deep learning framework for traffic forecasting

   Bing Yu ,  Haoteng Yin ,  and  Zhanxing Zhu

   In International Joint Conference of Artificial Intelligence (IJCAI) , 2018

   PDF
2. NIPS

   Reinforced continual learning

   Ju Xu ,  and  Zhanxing Zhu

   In Advances in Neural Information Processing Systems (NeurIPS) , 2018
3. CCS

   Yet another text captcha solver: A generative adversarial network based approach

   Guixin Ye ,  Zhanyong Tang ,  Dingyi Fang ,  Zhanxing Zhu ,  Yansong Feng ,  Pengfei Xu , and 2 more authors

   In Proceedings of the 2018 ACM SIGSAC conference on computer and communications security (ACM CCS) , 2018
4. ISBI

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

   Huizhuo Yuan ,  Jinzhu Jia ,  and  Zhanxing Zhu

   In 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI) , 2018
5. IJCAI

   Stochastic Fractional Hamiltonian Monte Carlo.

   Nanyang Ye ,  and  Zhanxing Zhu

   In IJCAI , 2018
6. NIPS

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

   Rui Luo ,  Jianhong Wang ,  Yaodong Yang ,  Jun Wang ,  and  Zhanxing Zhu

   Advances in Neural Information Processing Systems (NIPS), 2018
7. NIPS

   Bayesian adversarial learning

   Nanyang Ye ,  and  Zhanxing Zhu

   Advances in Neural Information Processing Systems (NIPS), 2018

2017

1. ICML

   Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes

   Lei Wu ,  and  Zhanxing Zhu

   In The 34th International Conference on Machine Learning (ICML 2017): Theoretical Machine Learning Workshop , 2017
2. NIPS

   Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks

   Nanyang Ye ,  Zhanxing Zhu ,  and  Rafal K Mantiuk

   In 31st Neural Information Processing Systems (NIPS) , 2017
3. ACL

   Learning with noise: Enhance distantly supervised relation extraction with dynamic transition matrix

   Bingfeng Luo ,  Yansong Feng ,  Zheng Wang ,  Zhanxing Zhu ,  Songfang Huang ,  Rui Yan , and 1 more author

   In ACL , 2017

2016

1. AAAI

   Stochastic parallel block coordinate descent for large-scale saddle point problems

   Zhanxing Zhu ,  and  Amos Storkey

   In Proceedings of the AAAI Conference on Artificial Intelligence , 2016

2015

1. ECML

   Adaptive stochastic primal-dual coordinate descent for separable saddle point problems

   Zhanxing Zhu ,  and  Amos J Storkey

   In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2015, Porto, Portugal, September 7-11, 2015, Proceedings, Part I 15 , 2015
2. ECML

   Aggregation under bias: Rényi divergence aggregation and its implementation via machine learning markets

   Amos J Storkey ,  Zhanxing Zhu ,  and  Jinli Hu

   In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2015, Porto, Portugal, September 7-11, 2015, Proceedings, Part I 15 , 2015
3. NIPS

   Covariance-controlled adaptive Langevin thermostat for large-scale Bayesian sampling

   Xiaocheng Shang ,  Zhanxing Zhu ,  Benedict Leimkuhler ,  and  Amos J Storkey

   In NIPS , 2015

2013

1. NPL

   Supervised distance preserving projections

   Zhanxing Zhu ,  Timo Similä ,  and  Francesco Corona

   Neural processing letters, 2013
2. Multiplicative updates for learning with stochastic matrices

   Zhanxing Zhu ,  Zhirong Yang ,  and  Erkki Oja

   In Image Analysis: 18th Scandinavian Conference, SCIA 2013, Espoo, Finland, June 17-20, 2013. Proceedings 18 , 2013

2011

1. IFAC

   Local linear regression for soft-sensor design with application to an industrial deethanizer

   Zhanxing Zhu ,  Francesco Corona ,  Amaury Lendasse ,  Roberto Baratti ,  and  Jose A Romagnoli

   IFAC Proceedings Volumes, 2011

2010

1. Automatic rank determination in projective nonnegative matrix factorization

   Zhirong Yang ,  Zhanxing Zhu ,  and  Erkki Oja

   In International Conference on Latent Variable Analysis and Signal Separation , 2010