mlsanityData to 7 Oct 2026

Multivariate Time Series Forecasting with Latent Graph Inference

arXiv 2203.03423 ↗First posted 7 Mar 2022cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series. Its modularity allows it to be integrated with current univariate methods. Our approach allows to trade-off accuracy and computational efficiency gradually via offering on one extreme inference of a potentially fully-connected graph or on another extreme a bipartite graph. In the potentially fully-connected case we consider all pair-wise interactions among time-series which yields the best forecasting accuracy. Conversely, the bipartite case leverages the dependency structure by inter-communicating the N time series through a small set of K auxiliary nodes that we introduce. This reduces the time and memory complexity w.r.t. previous graph inference methods from O(N^2) to O(NK) with a small trade-off in accuracy. We demonstrate the effectiveness of our model in a variety of datasets where both of its variants perform better or very competitively to previous graph inference methods in terms of forecasting accuracy and time efficiency.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 41 of its 58 references that are in the map. First posted on arXiv 7 Mar 2022.

Builds on

41 of 58 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  10. 2021E(n) Equivariant Graph Neural Networkscited by 951
  11. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  12. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
29 more
  1. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  2. 2019Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecastingcited by 748
  3. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  4. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  5. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  6. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  7. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 399
  8. 2018Neural Relational Inference for Interacting Systemscited by 339
  9. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
  10. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  11. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  12. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  13. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 298
  14. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
  15. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  16. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  17. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 169
  18. 2019High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processescited by 147
  19. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 142
  20. 2018Temporal Pattern Attention for Multivariate Time Series Forecastingcited by 125
  21. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 112
  22. 2019Deep Factors for Forecastingcited by 86
  23. 2020Differentiable Graph Module (DGM) for Graph Convolutional Networkscited by 86
  24. 2020Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globalitycited by 70
  25. 2019Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecastingcited by 69
  26. 2019Probabilistic Forecasting with Temporal Convolutional Neural Networkcited by 63
  27. 2020MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attentioncited by 29
  28. 2019Sales Demand Forecast in E-commerce using a Long Short-Term Memory Neural Network Methodologycited by 18
  29. 2021A Study of Joint Graph Inference and Forecastingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 7; 2024: 3; 2025: 4; 2026: 1.

20 papers.

Sort:

  1. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  2. 2022Scalable Spatiotemporal Graph Neural Networkscited by 52
  3. 2023Taming Local Effects in Graph-based Spatiotemporal Forecastingcited by 37
  4. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  5. 2022Sparse Graph Learning from Spatiotemporal Time Seriescited by 22
  6. 2023Graph-based Time Series Clustering for End-to-End Hierarchical Forecastingcited by 16
  7. 2025Relational Conformal Prediction for Correlated Time Seriescited by 11
  8. 2024Joint Estimation and Prediction of City-wide Delivery Demand: A Large Language Model Empowered Graph-based Learning Approachcited by 6
  9. 2025Over-squashing in Spatiotemporal Graph Neural Networkscited by 6
  10. 2022AZ-whiteness test: a test for uncorrelated noise on spatio-temporal graphscited by 5
  11. 2024Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learningcited by 5
  12. 2022Contextually Enhanced ES-dRNN with Dynamic Attention for Short-Term Load Forecastingcited by 4
8 more
  1. 2023Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scalecited by 3
  2. 2023Forecasting Irregularly Sampled Time Series using Graphscited by 1
  3. 2023GEANN: Scalable Graph Augmentations for Multi-Horizon Time Series Forecastingcited by 1
  4. 2024On the Regularization of Learnable Embeddings for Time Series Forecastingcited by 1
  5. 2022Modeling Oceanic Variables with Dynamic Graph Neural Networkscited by 0
  6. 2025Spatiotemporal Graph Neural Networks in short term load forecasting: Does adding Graph Structure in Consumption Data Improve Predictions?cited by 0
  7. 2025Select, then Balance: Exploring Exogenous Variable Modeling of Spatio-Temporal Forecastingcited by 0
  8. 2026AdaKernel: Learning Adaptive Kernel Parameters for Spatiotemporal Graph Neural Networkscited by 0