mlsanityData to 7 Oct 2026

Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-series

arXiv 2203.03991 ↗First posted 8 Mar 2022cs.LG q-fin.CPcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose an end-to-end architecture for multivariate time-series prediction that integrates a spatial-temporal graph neural network with a matrix filtering module. This module generates filtered (inverse) correlation graphs from multivariate time series before inputting them into a GNN. In contrast with existing sparsification methods adopted in graph neural network, our model explicitly leverage time-series filtering to overcome the low signal-to-noise ratio typical of complex systems data. We present a set of experiments, where we predict future sales from a synthetic time-series sales dataset. The proposed spatial-temporal graph neural network displays superior performances with respect to baseline approaches, with no graphical information, and with fully connected, disconnected graphs and unfiltered graphs.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 86 references that are in the map. First posted on arXiv 8 Mar 2022.

Builds on

36 of 86 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  4. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  5. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
  6. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  7. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  8. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  9. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  10. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  11. 2016Language Modeling with Gated Convolutional Networkscited by 688
  12. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
24 more
  1. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  2. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 433
  3. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
  4. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
  5. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 267
  6. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  7. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  8. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  9. 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
  10. 2019Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecastingcited by 69
  11. 2020Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networkscited by 64
  12. 2019Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysiscited by 27
  13. 2021Deep Reinforcement Learning for Active High Frequency Tradingcited by 21
  14. 2015Network Filtering for Big Data: Triangulated Maximally Filtered Graphcited by 17
  15. 2016Parsimonious modeling with Information Filtering Networkscited by 14
  16. 2020Deep Learning modeling of Limit Order Book: a comparative perspectivecited by 11
  17. 2021Integrating LSTMs and GNNs for COVID-19 Forecastingcited by 8
  18. 2021wsGAT: Weighted and Signed Graph Attention Networks for Link Predictioncited by 8
  19. 2019Learning Clique Forestscited by 7
  20. 2021Combining Graph Neural Networks and Spatio-temporal Disease Models to Predict COVID-19 Cases in Germanycited by 7
  21. 2020Topological regularization with information filtering networkscited by 6
  22. 2017Sparse causality network retrieval from short time seriescited by 4
  23. 2018Forecasting market statescited by 4
  24. 2016Matrix Neural Networkscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1; 2025: 1.

5 papers.

  1. 2024Deep Limit Order Book Forecastingcited by 7
  2. 2023Topological Feature Selectioncited by 3
  3. 2023Mitigating Cold-start Forecasting using Cold Causal Demand Forecasting Modelcited by 2
  4. 2025DynaGraph: Interpretable Multi-Label Prediction from EHRs via Dynamic Graph Learning and Contrastive Augmentationcited by 2
  5. 2023Domain-adapted Learning and Imitation: DRL for Power Arbitragecited by 0