mlsanityData to 7 Oct 2026

Graph-Guided Network for Irregularly Sampled Multivariate Time Series

arXiv 2110.05357 ↗First posted 11 Oct 2021cs.LG cs.AIcited by 110

Not on the map. Why?

Abstract (arXiv)

In many domains, including healthcare, biology, and climate science, time series are irregularly sampled with varying time intervals between successive readouts and different subsets of variables (sensors) observed at different time points. Here, we introduce RAINDROP, a graph neural network that embeds irregularly sampled and multivariate time series while also learning the dynamics of sensors purely from observational data. RAINDROP represents every sample as a separate sensor graph and models time-varying dependencies between sensors with a novel message passing operator. It estimates the latent sensor graph structure and leverages the structure together with nearby observations to predict misaligned readouts. This model can be interpreted as a graph neural network that sends messages over graphs that are optimized for capturing time-varying dependencies among sensors. We use RAINDROP to classify time series and interpret temporal dynamics on three healthcare and human activity datasets. RAINDROP outperforms state-of-the-art methods by up to 11.4% (absolute F1-score points), including techniques that deal with irregular sampling using fixed discretization and set functions. RAINDROP shows superiority in diverse setups, including challenging leave-sensor-out settings.

Key facts. Cited by 110 papers in the map (data through 7 Oct 2026). Builds on 41 of its 67 references that are in the map. First posted on arXiv 11 Oct 2021.

Builds on

41 of 67 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2018Neural Ordinary Differential Equationscited by 3,733
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  10. 2020Heterogeneous Graph Transformercited by 581
  11. 2018Deep learning for time series classification: a reviewcited by 575
  12. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
29 more
  1. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  2. 2019Graph Transformer Networkscited by 520
  3. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  4. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  5. 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 308
  6. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 270
  7. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 234
  8. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 181
  9. 2019Set Functions for Time Seriescited by 137
  10. 2016Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequencescited by 98
  11. 2020Compressing Large-Scale Transformer-Based Models: A Case Study on BERTcited by 95
  12. 2019Interpolation-Prediction Networks for Irregularly Sampled Time Seriescited by 89
  13. 2019Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformercited by 88
  14. 2021Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attentioncited by 86
  15. 2020Message Passing for Hyper-Relational Knowledge Graphscited by 78
  16. 2019Dynamic Graph Message Passing Networkscited by 62
  17. 2020Hierarchical Inter-Message Passing for Learning on Molecular Graphscited by 59
  18. 2020A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Seriescited by 42
  19. 2018A review on distance based time series classificationcited by 40
  20. 2020Learning from Irregularly-Sampled Time Series: A Missing Data Perspectivecited by 40
  21. 2020Time Series Data Imputation: A Survey on Deep Learning Approachescited by 34
  22. 2021Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Seriescited by 30
  23. 2016A scalable end-to-end Gaussian process adapter for irregularly sampled time series classificationcited by 27
  24. 2019Message Passing Attention Networks for Document Understandingcited by 23
  25. 2018Variational Message Passing with Structured Inference Networkscited by 17
  26. 2020Graph Mixture Density Networkscited by 9
  27. 2019Time series cluster kernels to exploit informative missingness and incomplete label informationcited by 6
  28. 2021Multi-Task Time Series Forecasting With Shared Attentioncited by 6
  29. 2020Improving Irregularly Sampled Time Series Learning with Dense Descriptors of Timecited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 25; 2024: 32; 2025: 20; 2026: 25.

110 papers.

Sort:

By area:

  1. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
  2. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  3. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  4. 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Seriescited by 79
  5. 2023Deep Learning for Time Series Classification and Extrinsic Regression: A Current Surveycited by 68
  6. 2024FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusioncited by 67
  7. 2023Domain Adaptation for Time Series Under Feature and Label Shiftscited by 60
  8. 2023Asynchrony-Robust Collaborative Perception via Bird's Eye View Flowcited by 58
  9. 2022Multimodal learning with graphscited by 54
  10. 2023Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Seriescited by 54
  11. 2025Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baselinecited by 54
  12. 2022GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networkscited by 43
38 more
  1. 2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
  2. 2022Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modelingcited by 33
  3. 2022Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Modelscited by 29
  4. 2023MBrain: A Multi-channel Self-Supervised Learning Framework for Brain Signalscited by 26
  5. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  6. 2024Population Transformer: Learning Population-level Representations of Neural Activitycited by 26
  7. 2022Sparse Graph Learning from Spatiotemporal Time Seriescited by 22
  8. 2023MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEscited by 19
  9. 2023Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networkcited by 19
  10. 2023DuETT: Dual Event Time Transformer for Electronic Health Recordscited by 17
  11. 2025HyperIMTS: Hypergraph Neural Network for Irregular Multivariate Time Series Forecastingcited by 14
  12. 2023Event-Based Contrastive Learning for Medical Time Seriescited by 13
  13. 2025CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Datacited by 12
  14. 2024Unleashing The Power of Pre-Trained Language Models for Irregularly Sampled Time Seriescited by 10
  15. 2024TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysiscited by 10
  16. 2024Intrinsic User-Centric Interpretability through Global Mixture of Expertscited by 9
  17. 2023Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classificationcited by 8
  18. 2024TimEHR: Image-based Time Series Generation for Electronic Health Recordscited by 8
  19. 2024SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Predictioncited by 8
  20. 2026Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecastingcited by 8
  21. 2022RIPPLE: Concept-Based Interpretation for Raw Time Series Models in Educationcited by 7
  22. 2023Temporal Graph Neural Networks for Irregular Datacited by 7
  23. 2024LITE: Modeling Environmental Ecosystems with Multimodal Large Language Modelscited by 7
  24. 2025ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecastingcited by 7
  25. 2024CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysiscited by 6
  26. 2023IVP-VAE: Modeling EHR Time Series with Initial Value Problem Solverscited by 5
  27. 2023On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Seriescited by 5
  28. 2024How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputationcited by 5
  29. 2023Graph State-Space Models and Latent Relational Inferencecited by 4
  30. 2024Cross-domain Learning Framework for Tracking Users in RIS-aided Multi-band ISAC Systems with Sparse Labeled Datacited by 4
  31. 2024Irregularity-Informed Time Series Analysis: Adaptive Modelling of Spatial and Temporal Dynamicscited by 4
  32. 2023Graph AI in Medicinecited by 3
  33. 2023Knowledge Graph Representations to enhance Intensive Care Time-Series Predictionscited by 3
  34. 2023TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcarecited by 3
  35. 2024TEE4EHR: Transformer Event Encoder for Better Representation Learning in Electronic Health Recordscited by 3
  36. 2024Disentangling Imperfect: A Wavelet-Infused Multilevel Heterogeneous Network for Human Activity Recognition in Flawed Wearable Sensor Datacited by 3
  37. 2024Temporal Cross-Attention for Dynamic Embedding and Tokenization of Multimodal Electronic Health Recordscited by 3
  38. 2023Compatible Transformer for Irregularly Sampled Multivariate Time Seriescited by 2

50 most cited of 110 All 110 (JSON)