mlsanityData to 14 Oct 2026

MuSiCNet: A Gradual Coarse-to-Fine Framework for Irregularly Sampled Multivariate Time Series Analysis

arXiv 2412.01063 ↗First posted 2 Dec 2024cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Irregularly sampled multivariate time series (ISMTS) are prevalent in reality. Most existing methods treat ISMTS as synchronized regularly sampled time series with missing values, neglecting that the irregularities are primarily attributed to variations in sampling rates. In this paper, we introduce a novel perspective that irregularity is essentially relative in some senses. With sampling rates artificially determined from low to high, an irregularly sampled time series can be transformed into a hierarchical set of relatively regular time series from coarse to fine. We observe that additional coarse-grained relatively regular series not only mitigate the irregularly sampled challenges to some extent but also incorporate broad-view temporal information, thereby serving as a valuable asset for representation learning. Therefore, following the philosophy of learning that Seeing the big picture first, then delving into the details, we present the Multi-Scale and Multi-Correlation Attention Network (MuSiCNet) combining multiple scales to iteratively refine the ISMTS representation. Specifically, within each scale, we explore time attention and frequency correlation matrices to aggregate intra- and inter-series information, naturally enhancing the representation quality with richer and more intrinsic details. While across adjacent scales, we employ a representation rectification method containing contrastive learning and reconstruction results adjustment to further improve representation consistency. MuSiCNet is an ISMTS analysis framework that competitive with SOTA in three mainstream tasks consistently, including classification, interpolation, and forecasting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 80 references that are in the map. First posted on arXiv 2 Dec 2024.

Builds on

46 of 80 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2018Neural Ordinary Differential Equationscited by 3,779
  4. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  5. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  6. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  7. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  8. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  9. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  10. 2021Multiscale Vision Transformerscited by 897
  11. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  12. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
34 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. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  4. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  5. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  6. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  7. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 238
  8. 2019GRU-ODE-Bayes: Continuous modeling of sporadically-observed time seriescited by 231
  9. 2019Time2Vec: Learning a Vector Representation of Timecited by 213
  10. 2021Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encodingcited by 207
  11. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  12. 2019Set Functions for Time Seriescited by 138
  13. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 111
  14. 2024Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecastingcited by 104
  15. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 103
  16. 2021Hierarchical Transformers Are More Efficient Language Modelscited by 102
  17. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 101
  18. 2016Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequencescited by 99
  19. 2019Interpolation-Prediction Networks for Irregularly Sampled Time Seriescited by 89
  20. 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Seriescited by 79
  21. 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
  22. 2024Deep Learning for Multivariate Time Series Imputation: A Surveycited by 57
  23. 2023Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Seriescited by 55
  24. 2022Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecastingcited by 54
  25. 2023MSGNet: Learning Multi-Scale Inter-Series Correlations for Multivariate Time Series Forecastingcited by 50
  26. 2020A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Seriescited by 42
  27. 2021Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Seriescited by 30
  28. 2022EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecastingcited by 22
  29. 2019Improving Missing Data Imputation with Deep Generative Modelscited by 19
  30. 2021TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Datacited by 10
  31. 2019Multi-resolution Networks For Flexible Irregular Time Series Modeling (Multi-FIT)cited by 7
  32. 2021LIFE: Learning Individual Features for Multivariate Time Series Prediction with Missing Valuescited by 5
  33. 2022NIERT: Accurate Numerical Interpolation through Unifying Scattered Data Representations using Transformer Encodercited by 4
  34. 2024Imputation with Inter-Series Information from Prototypes for Irregular Sampled Time Seriescited by 2

Built on by

Not cited yet.