English

Adaptive Structured Pruning of Convolutional Neural Networks for Time Series Classification

Machine Learning 2026-02-16 v1

Abstract

Deep learning models for Time Series Classification (TSC) have achieved strong predictive performance but their high computational and memory requirements often limit deployment on resource-constrained devices. While structured pruning can address these issues by removing redundant filters, existing methods typically rely on manually tuned hyperparameters such as pruning ratios which limit scalability and generalization across datasets. In this work, we propose Dynamic Structured Pruning (DSP), a fully automatic, structured pruning framework for convolution-based TSC models. DSP introduces an instance-wise sparsity loss during training to induce channel-level sparsity, followed by a global activation analysis to identify and prune redundant filters without needing any predefined pruning ratio. This work tackles computational bottlenecks of deep TSC models for deployment on resource-constrained devices. We validate DSP on 128 UCR datasets using two different deep state-of-the-art architectures: LITETime and InceptionTime. Our approach achieves an average compression of 58% for LITETime and 75% for InceptionTime architectures while maintaining classification accuracy. Redundancy analyses confirm that DSP produces compact and informative representations, offering a practical path for scalable and efficient deep TSC deployment.

Keywords

Cite

@article{arxiv.2602.12744,
  title  = {Adaptive Structured Pruning of Convolutional Neural Networks for Time Series Classification},
  author = {Javidan Abdullayev and Maxime Devanne and Cyril Meyer and Ali Ismail-Fawaz and Jonathan Weber and Germain Forestier},
  journal= {arXiv preprint arXiv:2602.12744},
  year   = {2026}
}

Comments

12 pages, 16 figures. Accepted at ICAART 2026

R2 v1 2026-07-01T10:35:01.010Z