mlsanityData to 14 Oct 2026

GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing

arXiv 2405.11333 ↗First posted 18 May 2024cs.LG cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

Multivariate time series forecasting (MTSF) is crucial for decision-making to precisely forecast the future values/trends, based on the complex relationships identified from historical observations of multiple sequences. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have gradually become the theme of MTSF model as their powerful capability in mining spatial-temporal dependencies, but almost of them heavily rely on the assumption of historical data integrity. In reality, due to factors such as data collector failures and time-consuming repairment, it is extremely challenging to collect the whole historical observations without missing any variable. In this case, STGNNs can only utilize a subset of normal variables and easily suffer from the incorrect spatial-temporal dependency modeling issue, resulting in the degradation of their forecasting performance. To address the problem, in this paper, we propose a novel Graph Interpolation Attention Recursive Network (named GinAR) to precisely model the spatial-temporal dependencies over the limited collected data for forecasting. In GinAR, it consists of two key components, that is, interpolation attention and adaptive graph convolution to take place of the fully connected layer of simple recursive units, and thus are capable of recovering all missing variables and reconstructing the correct spatial-temporal dependencies for recursively modeling of multivariate time series data, respectively. Extensive experiments conducted on five real-world datasets demonstrate that GinAR outperforms 11 SOTA baselines, and even when 90% of variables are missing, it can still accurately predict the future values of all variables.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 33 of its 78 references that are in the map. First posted on arXiv 18 May 2024.

Builds on

33 of 78 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  4. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  5. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  6. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  7. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 401
  8. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  9. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  10. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 172
  11. 2021Discrete Graph Structure Learning for Forecasting Multiple Time Seriescited by 171
  12. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
21 more
  1. 2022Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecastingcited by 151
  2. 2023FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspectivecited by 127
  3. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 123
  4. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  5. 2023Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysiscited by 117
  6. 2020Inductive Graph Neural Networks for Spatiotemporal Krigingcited by 91
  7. 2022Spatio-Temporal Meta-Graph Learning for Traffic Forecastingcited by 88
  8. 2021DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Predictioncited by 73
  9. 2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
  10. 2023DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Predictioncited by 49
  11. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  12. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  13. 2019Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Valuescited by 37
  14. 2023GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputationcited by 35
  15. 2022Self-supervised Hypergraph Representation Learning for Sociological Analysiscited by 27
  16. 2021NRTSI: Non-Recurrent Time Series Imputationcited by 25
  17. 2020VEST: Automatic Feature Engineering for Forecastingcited by 14
  18. 2018Imputation of Clinical Covariates in Time Seriescited by 10
  19. 2022Multi-Variate Time Series Forecasting on Variable Subsetscited by 5
  20. 2023SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchiescited by 5
  21. 2022Sequence Prediction Under Missing Data : An RNN Approach Without Imputationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 13; 2026: 2.

20 papers.

Sort:

By area:

  1. 2024DUET: Dual Clustering Enhanced Multivariate Time Series Forecastingcited by 107
  2. 2025Patch-wise Structural Loss for Time Series Forecastingcited by 35
  3. 2025LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimizationcited by 22
  4. 2025Merlin: Multi-View Representation Learning for Robust Multivariate Time Series Forecasting with Unfixed Missing Ratescited by 20
  5. 2025TimeMosaic: Temporal Heterogeneity Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decodingcited by 12
  6. 2025Deep Learning for Time Series Forecasting: A Surveycited by 10
  7. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  8. 2025K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecastingcited by 8
  9. 2025Selective Learning for Deep Time Series Forecastingcited by 8
  10. 2025DualSG: A Dual-Stream Explicit Semantic-Guided Multivariate Time Series Forecasting Frameworkcited by 7
  11. 2025Revisiting Multivariate Time Series Forecasting with Missing Valuescited by 7
  12. 2024A Survey of Spatio-Temporal EEG data Analysis: from Models to Applicationscited by 3
8 more
  1. 2024Online Policy Distillation with Decision-Attentioncited by 2
  2. 2025IBN: An Interpretable Bidirectional-Modeling Network for Multivariate Time Series Forecasting with Variable Missingcited by 1
  3. 2026DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Versioncited by 1
  4. 2024Spatio-Temporal Partial Sensing Forecast for Long-term Trafficcited by 0
  5. 2025GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Valuescited by 0
  6. 2025Spatio-temporal Multivariate Time Series Forecast with Chosen Variablescited by 0
  7. 2025STeP-Diff: Spatio-Temporal Physics-Informed Diffusion Models for Mobile Fine-Grained Pollution Forecastingcited by 0
  8. 2026Frequency-Domain Multi-Modality Transportation Modelingcited by 0