Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
Explore this paper's citation graph
Summary
Spectral Temporal Graph Neural Network (StemGNN) is proposed to further improve the accuracy of multivariate time-series forecasting and learns inter-series correlations automatically from the data without using pre-defined priors.
- Type
- article
- Published
- 2020-11-06
- Cited by
- 815
- References
- 41
- Access
- Open access
- OpenAlex
- https://openalex.org/W3104302219
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:227276243
Keywords
Series (stratigraphy), Multivariate statistics, Computer science, Time series, Convolution (computer science)
References
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
- Freeway Performance Measurement System: Mining Loop Detector Data
- Predicting stock market index using fusion of machine learning techniques
- Another look at measures of forecast accuracy
- Recurrent neural network and a hybrid model for prediction of stock returns
- Long Short-Term Memory
- Big data and its technical challenges
- Birds of a Feather: Homophily in Social Networks
- Forecasting Sales by Exponentially Weighted Moving Averages
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
- Stationary time-vertex signal processing
- Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
- DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
- A Time-Vertex Signal Processing Framework: Scalable Processing and Meaningful Representations for Time-Series on Graphs
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
- Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- Deep State Space Models for Time Series Forecasting
- Graph Neural Networks: A Review of Methods and Applications
- A Comprehensive Survey on Graph Neural Networks
Cited by
- Graph Neural Network for Traffic Forecasting: A Survey
- Predicting the Dynamics of the COVID-19 Pandemic in the United States Using Graph Theory-Based Neural Networks
- Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT
- Forecasting Interaction Order on Temporal Graphs
- Accurate Multivariate Stock Movement Prediction via Data-Axis Transformer with Multi-Level Contexts
- Spatial-temporal graph neural network for traffic forecasting: An overview and open research issues
- Deep Autoregressive Models with Spectral Attention
- Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
- ETA Prediction with Graph Neural Networks in Google Maps
- DeepExpress: Heterogeneous and Coupled Sequence Modeling for Express Delivery Prediction
- Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction
- TS2Vec: Towards Universal Representation of Time Series
- Spectral Temporal Graph Neural Network for Trajectory Prediction
- Generating Complex, Realistic Cloud Workloads using Recurrent Neural Networks
- MTP: Multi-hypothesis Tracking and Prediction for Reduced Error Propagation
- HierST: A Unified Hierarchical Spatial-temporal Framework for COVID-19 Trend Forecasting
- Attention Based Dynamic Graph Learning Framework for Asset Pricing
- Multi-task attributed graphical lasso and its application in fund classification
- Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting
- Context Integrated Relational Spatio-Temporal Resource Forecasting