Timezone: »
Multivariate time-series forecasting plays a crucial role in many real-world applications. It is a challenging problem as one needs to consider both intra-series temporal correlations and inter-series correlations simultaneously. Recently, there have been multiple works trying to capture both correlations, but most, if not all of them only capture temporal correlations in the time domain and resort to pre-defined priors as inter-series relationships.
In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting. StemGNN captures inter-series correlations and temporal dependencies jointly in the spectral domain. It combines Graph Fourier Transform (GFT) which models inter-series correlations and Discrete Fourier Transform (DFT) which models temporal dependencies in an end-to-end framework. After passing through GFT and DFT, the spectral representations hold clear patterns and can be predicted effectively by convolution and sequential learning modules. Moreover, StemGNN learns inter-series correlations automatically from the data without using pre-defined priors. We conduct extensive experiments on ten real-world datasets to demonstrate the effectiveness of StemGNN.
Author Information
Defu Cao (Peking University)
Yujing Wang (MSRA)
Juanyong Duan (Microsoft)
Ce Zhang (ETH Zurich)
Xia Zhu (Microsoft)
Congrui Huang (Microsoft)
Yunhai Tong (Peking University)
Bixiong Xu (Microsoft)
Jing Bai (Microsoft)
Jie Tong (Microsoft)
Qi Zhang (Microsoft)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Poster: Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting »
Thu. Dec 10th 05:00 -- 07:00 AM Room Poster Session 4 #1170
More from the Same Authors
-
2021 : Evaluating Bayes Error Estimators on Real-World Datasets with FeeBee »
Cedric Renggli · Luka Rimanic · Nora Hollenstein · Ce Zhang -
2021 : WRENCH: A Comprehensive Benchmark for Weak Supervision »
Jieyu Zhang · Yue Yu · · Yujing Wang · Yaming Yang · Mao Yang · Alexander Ratner -
2021 : WRENCH: A Comprehensive Benchmark for Weak Supervision »
Jieyu Zhang · Yue Yu · · Yujing Wang · Yaming Yang · Mao Yang · Alexander Ratner -
2021 Poster: TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness »
Zhuolin Yang · Linyi Li · Xiaojun Xu · Shiliang Zuo · Qian Chen · Pan Zhou · Benjamin Rubinstein · Ce Zhang · Bo Li -
2020 Poster: Learning to Mutate with Hypergradient Guided Population »
Zhiqiang Tao · Yaliang Li · Bolin Ding · Ce Zhang · Jingren Zhou · Yun Fu -
2020 Poster: On Convergence of Nearest Neighbor Classifiers over Feature Transformations »
Luka Rimanic · Cedric Renggli · Bo Li · Ce Zhang -
2018 Poster: Communication Compression for Decentralized Training »
Hanlin Tang · Shaoduo Gan · Ce Zhang · Tong Zhang · Ji Liu -
2017 Poster: Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent »
Xiangru Lian · Ce Zhang · Huan Zhang · Cho-Jui Hsieh · Wei Zhang · Ji Liu -
2017 Oral: Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent »
Xiangru Lian · Ce Zhang · Huan Zhang · Cho-Jui Hsieh · Wei Zhang · Ji Liu