Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

@article{Jin2022MultivariateTS,
  title={Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs},
  author={Ming Jin and Yu Zheng and Yuanhao Li and Siheng Chen and B. Yang and Shirui Pan},
  journal={ArXiv},
  year={2022},
  volume={abs/2202.08408}
}
—Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction. While recent methods demonstrate good forecasting abilities, they have three fundamental limitations. (i). Discrete neural architectures : Interlacing individually parameterized spatial and temporal blocks to encode rich underlying patterns leads to discontinuous latent state trajectories and higher forecasting numerical errors. (ii). High… 
[PDF] Semantic Reader

Figures and Tables from this paper

References

SHOWING 1-10 OF 38 REFERENCES

Modeling Temporal Patterns with Dilated Convolutions for Time-Series Forecasting

The proposed HyDCNN is a novel hybrid framework based on fully Dilated CNN for time-series forecasting tasks, in which the proposed position-aware dilated CNNs are utilized to capture the sequential non-linear dynamics and an autoregressive model is leveraged to captured the sequential linear dependencies.

Learning representations by back-propagating errors

Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Qualitatively, the proposed RNN Encoder‐Decoder model learns a semantically and syntactically meaningful representation of linguistic phrases.

Graph Neural Controlled Differential Equations for Traffic Forecasting

The method of spatio-temporal graph neural controlled differential equation (STG-NCDE) shows the best accuracy in all cases, outperforming all those 20 baselines by non-trivial margins.

Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting

This work proposes Spatial-Temporal Graph Ordinary Differential Equation Networks (STGODE), which captures spatial-temporal dynamics through a tensor-based ordinary differential equation (ODE), as a result, deeper networks can be constructed and spatial- Temporal features are utilized synchronously.

Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

This paper proposes a general graph neural network framework designed specifically for multivariate time series data that outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information.

Discrete Graph Structure Learning for Forecasting Multiple Time Series

This work proposes learning the structure simultaneously with the GNN if the graph is unknown, and casts the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution.

Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting

The Multi-Range Attentive Bicomponent GCN (MRA-BGCN), a novel deep learning model for traffic forecasting that introduces the multi-range attention mechanism to aggregate information in different neighborhood ranges and automatically learn the importance of different ranges.

GMAN: A Graph Multi-Attention Network for Traffic Prediction

Experimental results on two real-world traffic prediction tasks demonstrate the superiority of GMAN, and in the 1 hour ahead prediction, GMAN outperforms state-of-the-art methods by up to 4% improvement in MAE measure.

Graph WaveNet for Deep Spatial-Temporal Graph Modeling

This paper proposes a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling by developing a novel adaptive dependency matrix and learn it through node embedding, which can precisely capture the hidden spatial dependency in the data.