mlsanityData to 14 Oct 2026

TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning

arXiv 2405.03140 ↗First posted 6 May 2024cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully account for the sparsity and locality of patterns in time series data (e.g., diseases-related anomalous points in ECG). To address this challenge, we formally reformulate MTSC as a weakly supervised problem, introducing a novel multiple-instance learning (MIL) framework for better localization of patterns of interest and modeling time dependencies within time series. Our novel approach, TimeMIL, formulates the temporal correlation and ordering within a time-aware MIL pooling, leveraging a tokenized transformer with a specialized learnable wavelet positional token. The proposed method surpassed 26 recent state-of-the-art methods, underscoring the effectiveness of the weakly supervised TimeMIL in MTSC. The code will be available at https://github.com/xiwenc1/TimeMIL.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 37 of its 66 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

37 of 66 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  5. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  6. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  7. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  8. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  9. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  10. 2018Deep learning for time series classification: a reviewcited by 576
  11. 2021TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classificationcited by 555
  12. 2020Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learningcited by 478
25 more
  1. 2021Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attentioncited by 471
  2. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  3. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  4. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 387
  5. 2018Efficient Attention: Attention with Linear Complexitiescited by 368
  6. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 339
  7. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  8. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 336
  9. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  10. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 160
  11. 2020Benchmarking Multivariate Time Series Classification Algorithmscited by 145
  12. 2018Multivariate LSTM-FCNs for Time Series Classificationcited by 120
  13. 2016Revisiting Multiple Instance Neural Networkscited by 119
  14. 2022Flowformer: Linearizing Transformers with Conservation Flowscited by 69
  15. 2017Multivariate Time Series Classification with WEASEL+MUSEcited by 53
  16. 2023MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixingcited by 53
  17. 2020Omni-Scale CNNs: a simple and effective kernel size configuration for time series classificationcited by 48
  18. 2017Feature-based time-series analysiscited by 28
  19. 2023Inherently Interpretable Time Series Classification via Multiple Instance Learningcited by 23
  20. 2015Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognitioncited by 22
  21. 2023TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classificationcited by 16
  22. 2023PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layerscited by 6
  23. 2023SC-MIL: Sparsely Coded Multiple Instance Learning for Whole Slide Image Classificationcited by 6
  24. 2023MTS-LOF: Medical Time-Series Representation Learning via Occlusion-Invariant Featurescited by 5
  25. 2021Uncertainty-Aware Multiple Instance Learning from Large-Scale Long Time Series Datacited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 1.

12 papers.

  1. 2024DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classificationcited by 25
  2. 2025TIMING: Temporality-Aware Integrated Gradients for Time Series Explanationcited by 10
  3. 2025How Effective Can Dropout Be in Multiple Instance Learning ?cited by 7
  4. 2025Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecastingcited by 4
  5. 2025Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysiscited by 3
  6. 2025FIC-TSC: Learning Time Series Classification with Fisher Information Constraintcited by 2
  7. 2025Predicting symbolic ODEs from multiple trajectoriescited by 2
  8. 2025Smarter Together: Combining Large Language Models and Small Models for Physiological Signals Visual Inspectioncited by 1
  9. 2025Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgmentcited by 1
  10. 2024Set2Seq Transformer: Temporal and Position-Aware Set Representations for Sequential Multiple-Instance Learningcited by 0
  11. 2025Focus on What Matters: Constraining Spatial-Temporal Attention via Action-Units for Noise-Resilient AQAcited by 0
  12. 2026Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Seriescited by 0