Timezone: »
Many approaches have been proposed for time series forecasting, in light of its significance in wide applications including business demand prediction. However, the existing methods suffer from two key limitations. Firstly, most point prediction models only predict an exact value of each time step without flexibility, which can hardly capture the stochasticity of data. Even probabilistic prediction using the likelihood estimation suffers these problems in the same way. Besides, most of them use the auto-regressive generative mode, where ground-truth is provided during training and replaced by the network’s own one-step ahead output during inference, causing the error accumulation in inference. Thus they may fail to forecast time series for long time horizon due to the error accumulation. To solve these issues, in this paper, we propose a new time series forecasting model -- Adversarial Sparse Transformer (AST), based on Generated Adversarial Networks (GANs). Specifically, AST adopts a Sparse Transformer as the generator to learn a sparse attention map for time series forecasting, and uses a discriminator to improve the prediction performance from sequence level. Extensive experiments on several real-world datasets show the effectiveness and efficiency of our method.
Author Information
Sifan Wu (Tsinghua University)
Xi Xiao (Tsinghua University)
Qianggang Ding (Tsinghua University)
Peilin Zhao (Tencent AI Lab)
Ying Wei (Tencent AI Lab)
Junzhou Huang (University of Texas at Arlington / Tencent AI Lab)
More from the Same Authors
-
2020 Poster: Revisiting Parameter Sharing for Automatic Neural Channel Number Search »
Jiaxing Wang · Haoli Bai · Jiaxiang Wu · Xupeng Shi · Junzhou Huang · Irwin King · Michael Lyu · Jian Cheng -
2020 Poster: Dirichlet Graph Variational Autoencoder »
Jia Li · Jianwei Yu · Jiajin Li · Honglei Zhang · Kangfei Zhao · Yu Rong · Hong Cheng · Junzhou Huang -
2020 Poster: RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist »
Chaochao Yan · Qianggang Ding · Peilin Zhao · Shuangjia Zheng · JINYU YANG · Yang Yu · Junzhou Huang -
2020 Spotlight: RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist »
Chaochao Yan · Qianggang Ding · Peilin Zhao · Shuangjia Zheng · JINYU YANG · Yang Yu · Junzhou Huang -
2020 Poster: Self-Supervised Graph Transformer on Large-Scale Molecular Data »
Yu Rong · Yatao Bian · Tingyang Xu · Weiyang Xie · Ying WEI · Wenbing Huang · Junzhou Huang -
2020 Poster: Deep Multimodal Fusion by Channel Exchanging »
Yikai Wang · Wenbing Huang · Fuchun Sun · Tingyang Xu · Yu Rong · Junzhou Huang -
2019 Poster: Hyperparameter Learning via Distributional Transfer »
Ho Chung Law · Peilin Zhao · Leung Sing Chan · Junzhou Huang · Dino Sejdinovic -
2019 Poster: DTWNet: a Dynamic Time Warping Network »
Xingyu Cai · Tingyang Xu · Jinfeng Yi · Junzhou Huang · Sanguthevar Rajasekaran -
2019 Poster: NAT: Neural Architecture Transformer for Accurate and Compact Architectures »
Yong Guo · Yin Zheng · Mingkui Tan · Qi Chen · Jian Chen · Peilin Zhao · Junzhou Huang -
2019 Poster: Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement »
Chao Yang · Xiaojian Ma · Wenbing Huang · Fuchun Sun · Huaping Liu · Junzhou Huang · Chuang Gan -
2019 Spotlight: Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement »
Chao Yang · Xiaojian Ma · Wenbing Huang · Fuchun Sun · Huaping Liu · Junzhou Huang · Chuang Gan -
2018 Poster: Learning to Multitask »
Yu Zhang · Ying Wei · Qiang Yang -
2018 Poster: Discrimination-aware Channel Pruning for Deep Neural Networks »
Zhuangwei Zhuang · Mingkui Tan · Bohan Zhuang · Jing Liu · Yong Guo · Qingyao Wu · Junzhou Huang · Jinhui Zhu -
2018 Poster: Weakly Supervised Dense Event Captioning in Videos »
Xin Wang · Wenbing Huang · Chuang Gan · Jingdong Wang · Wenwu Zhu · Junzhou Huang -
2018 Poster: Adaptive Sampling Towards Fast Graph Representation Learning »
Wenbing Huang · Tong Zhang · Yu Rong · Junzhou Huang -
2017 Poster: Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding »
Wenbing Huang · Mehrtash Harandi · Tong Zhang · Lijie Fan · Fuchun Sun · Junzhou Huang -
2012 Poster: Compressive Sensing MRI with Wavelet Tree Sparsity »
Chen Chen · Junzhou Huang