mlsanityData to 14 Oct 2026

Investigating a Model-Agnostic and Imputation-Free Approach for Irregularly-Sampled Multivariate Time-Series Modeling

arXiv 2502.15785 ↗First posted 18 Feb 2025cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Modeling Irregularly-sampled and Multivariate Time Series (IMTS) is crucial across a variety of applications where different sets of variates may be missing at different time-steps due to sensor malfunctions or high data acquisition costs. Existing approaches for IMTS either consider a two-stage impute-then-model framework or involve specialized architectures specific to a particular model and task. We perform a series of experiments to derive novel insights about the performance of IMTS methods on a variety of semi-synthetic and real-world datasets for both classification and forecasting. We also introduce Missing Feature-aware Time Series Modeling (MissTSM) or MissTSM, a novel model-agnostic and imputation-free approach for IMTS modeling. We show that MissTSM shows competitive performance compared to other IMTS approaches, especially when the amount of missing values is large and the data lacks simplistic periodic structures - conditions common to real-world IMTS applications.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 60 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

34 of 60 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2018Neural Ordinary Differential Equationscited by 3,779
  6. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  7. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  8. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  9. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  10. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  11. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  12. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
22 more
  1. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  2. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  3. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  4. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  5. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
  6. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 250
  7. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 238
  8. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 172
  9. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  10. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 144
  11. 2023TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecastingcited by 139
  12. 2019Set Functions for Time Seriescited by 138
  13. 2023SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modelingcited by 115
  14. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 111
  15. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  16. 2016Modeling Missing Data in Clinical Time Series with RNNscited by 80
  17. 2023Ti-MAE: Self-Supervised Masked Time Series Autoencoderscited by 63
  18. 2024ContiFormer: Continuous-Time Transformer for Irregular Time Series Modelingcited by 63
  19. 2019NAOMI: Non-Autoregressive Multiresolution Sequence Imputationcited by 59
  20. 2020A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Seriescited by 42
  21. 2024RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomaliescited by 18
  22. 2023Compatible Transformer for Irregularly Sampled Multivariate Time Seriescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Datacited by 0