mlsanityData to 7 Oct 2026

Dynamic Sparse Network for Time Series Classification: Learning What to "see''

arXiv 2212.09840 ↗First posted 19 Dec 2022cs.LG cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

The receptive field (RF), which determines the region of time series to be ``seen'' and used, is critical to improve the performance for time series classification (TSC). However, the variation of signal scales across and within time series data, makes it challenging to decide on proper RF sizes for TSC. In this paper, we propose a dynamic sparse network (DSN) with sparse connections for TSC, which can learn to cover various RF without cumbersome hyper-parameters tuning. The kernels in each sparse layer are sparse and can be explored under the constraint regions by dynamic sparse training, which makes it possible to reduce the resource cost. The experimental results show that the proposed DSN model can achieve state-of-art performance on both univariate and multivariate TSC datasets with less than 50% computational cost compared with recent baseline methods, opening the path towards more accurate resource-aware methods for time series analyses. Our code is publicly available at: https://github.com/QiaoXiao7282/DSN.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 43 of its 61 references that are in the map. First posted on arXiv 19 Dec 2022.

Builds on

43 of 61 references.

References · 43

  1. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  2. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  3. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
  4. 2018Deep learning for time series classification: a reviewcited by 575
  5. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 521
  6. 2019Rigging the Lottery: Making All Tickets Winnerscited by 491
  7. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 475
  8. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 467
  9. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  10. 2018The UCR Time Series Archivecited by 421
  11. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
  12. 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
31 more
  1. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 336
  2. 2018The UEA multivariate time series classification archive, 2018cited by 330
  3. 2017Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Sciencecited by 325
  4. 2019Unsupervised Scalable Representation Learning for Multivariate Time Seriescited by 267
  5. 2019Sparse Networks from Scratch: Faster Training without Losing Performancecited by 210
  6. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 186
  7. 2020Soft Threshold Weight Reparameterization for Learnable Sparsitycited by 150
  8. 2018Multivariate LSTM-FCNs for Time Series Classificationcited by 120
  9. 2021HIVE-COTE 2.0: a new meta ensemble for time series classificationcited by 118
  10. 2021Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Trainingcited by 107
  11. 2016Multi-Scale Convolutional Neural Networks for Time Series Classificationcited by 99
  12. 2021Sparse Training via Boosting Pruning Plasticity with Neuroregenerationcited by 83
  13. 2021MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edgecited by 77
  14. 2018Temporal Convolutional Neural Network for the Classification of Satellite Image Time Seriescited by 76
  15. 2021Dynamic Sparse Training for Deep Reinforcement Learningcited by 49
  16. 2021Powerpropagation: A sparsity inducing weight reparameterisationcited by 49
  17. 2020Omni-Scale CNNs: a simple and effective kernel size configuration for time series classificationcited by 47
  18. 2018Proximity Forest: An effective and scalable distance-based classifier for time seriescited by 46
  19. 2021Efficient Lottery Ticket Finding: Less Data is Morecited by 44
  20. 2020The Lottery Ticket Hypothesis for Object Recognitioncited by 34
  21. 2016A topological insight into restricted Boltzmann machinescited by 32
  22. 2017On-line Building Energy Optimization using Deep Reinforcement Learningcited by 27
  23. 2021Selfish Sparse RNN Trainingcited by 26
  24. 2021Resolution learning in deep convolutional networks using scale-space theorycited by 26
  25. 2019Deep Neural Network Ensembles for Time Series Classificationcited by 13
  26. 2021Learnable Dynamic Temporal Pooling for Time Series Classificationcited by 13
  27. 2021Sparse Training Theory for Scalable and Efficient Agentscited by 12
  28. 2019Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networkscited by 7
  29. 2017Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognitioncited by 6
  30. 2020Residual Attention Net for Superior Cross-Domain Time Sequence Modelingcited by 2
  31. 2019Automatic alignment of surgical videos using kinematic datacited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 8; 2025: 4; 2026: 3.

22 papers.

Sort:

By area:

  1. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  2. 2024ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysiscited by 26
  3. 2023DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalizationcited by 24
  4. 2023E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentationcited by 16
  5. 2024Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustnesscited by 11
  6. 2023A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learningcited by 9
  7. 2023Are Large Kernels Better Teachers than Transformers for ConvNets?cited by 8
  8. 2024Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representationscited by 6
  9. 2025On the Interplay Between Sparsity and Training in Deep Reinforcement Learningcited by 3
  10. 2024DRFormer: Multi-Scale Transformer Utilizing Diverse Receptive Fields for Long Time-Series Forecastingcited by 2
  11. 2026AI Research Agents Narrow Scientific Explorationcited by 2
  12. 2023Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformerscited by 1
10 more
  1. 2024Are Sparse Neural Networks Better Hard Sample Learners?cited by 1
  2. 2025Empirical risk minimization algorithm for multiclass classification of S.D.E. pathscited by 1
  3. 2025Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolutioncited by 1
  4. 2023The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Needcited by 0
  5. 2023Unsupervised Multi-modal Feature Alignment for Time Series Representation Learningcited by 0
  6. 2024Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolingscited by 0
  7. 2024Omni-Dimensional Frequency Learner for General Time Series Analysiscited by 0
  8. 2025Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsitycited by 0
  9. 2026Learning to Test: Physics-Informed Representation for Dynamical Instability Detectioncited by 0
  10. 2026Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scalingcited by 0