# Adaptive Structured Pruning of Convolutional Neural Networks for Time Series Classification

arXiv: https://arxiv.org/abs/2602.12744 · HTML: https://mlsanity.com/paper/2602.12744/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures](https://mlsanity.com/paper/1607.03250/) (2016)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Data-free parameter pruning for Deep Neural Networks](https://mlsanity.com/paper/1507.06149/) (2015)
- [The Singular Values of Convolutional Layers](https://mlsanity.com/paper/1805.10408/) (2018)
- [MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification](https://mlsanity.com/paper/2102.00457/) (2021)
- [Pruning Convolutional Neural Networks for Resource Efficient Inference](https://mlsanity.com/paper/1611.06440/) (2016)
- [Proximity Forest: An effective and scalable distance-based classifier for time series](https://mlsanity.com/paper/1808.10594/) (2018)
- [An Approach to Multiple Comparison Benchmark Evaluations that is Stable Under Manipulation of the Comparate Set](https://mlsanity.com/paper/2305.11921/) (2023)
- [Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs](https://mlsanity.com/paper/1802.10280/) (2018)
- [Learning Instance-wise Sparsity for Accelerating Deep Models](https://mlsanity.com/paper/1907.11840/) (2019)
- [Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices](https://mlsanity.com/paper/2103.03483/) (2021)
- [KDCTime: Knowledge Distillation with Calibration on InceptionTime for Time-series Classification](https://mlsanity.com/paper/2112.02291/) (2021)

## Abstract (arXiv)

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.