Adaptive Structured Pruning of Convolutional Neural Networks for Time Series Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915796553302016 |
|---|---|
| author | Abdullayev, Javidan Devanne, Maxime Meyer, Cyril Ismail-Fawaz, Ali Weber, Jonathan Forestier, Germain |
| author_facet | Abdullayev, Javidan Devanne, Maxime Meyer, Cyril Ismail-Fawaz, Ali Weber, Jonathan Forestier, Germain |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12744 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive Structured Pruning of Convolutional Neural Networks for Time Series Classification Abdullayev, Javidan Devanne, Maxime Meyer, Cyril Ismail-Fawaz, Ali Weber, Jonathan Forestier, Germain Machine Learning 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. |
| title | Adaptive Structured Pruning of Convolutional Neural Networks for Time Series Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.12744 |