# Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1810.00518 · HTML: https://mlsanity.com/paper/1810.00518/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2018.

## Built on by (most cited first, 9 of 9)

- [Entropy Induced Pruning Framework for Convolutional Neural Networks](https://mlsanity.com/paper/2208.06660/) (2022)
- [Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions](https://mlsanity.com/paper/2108.13055/) (2021)
- [A2P-MANN: Adaptive Attention Inference Hops Pruned Memory-Augmented Neural Networks](https://mlsanity.com/paper/2101.09693/) (2021)
- [Supervised Robustness-preserving Data-free Neural Network Pruning](https://mlsanity.com/paper/2204.00783/) (2022)
- [Towards Building Efficient Sentence BERT Models using Layer Pruning](https://mlsanity.com/paper/2409.14168/) (2024)
- [Pruning On-the-Fly: A Recoverable Pruning Method without Fine-tuning](https://mlsanity.com/paper/2212.12651/) (2022)
- [Subspace Node Pruning](https://mlsanity.com/paper/2405.17506/) (2024)
- [On Importance of Layer Pruning for Smaller BERT Models and Low Resource Languages](https://mlsanity.com/paper/2501.00733/) (2025)
- [Projection-Free CNN Pruning via Frank-Wolfe with Momentum: Sparser Models with Less Pretraining](https://mlsanity.com/paper/2512.01147/) (2025)

## Abstract (arXiv)

Resource-efficient convolution neural networks enable not only the intelligence on edge devices but also opportunities in system-level optimization such as scheduling. In this work, we aim to improve the performance of resource-constrained filter pruning by merging two sub-problems commonly considered, i.e., (i) how many filters to prune for each layer and (ii) which filters to prune given a per-layer pruning budget, into a global filter ranking problem. Our framework entails a novel algorithm, dubbed layer-compensated pruning, where meta-learning is involved to determine better solutions. We show empirically that the proposed algorithm is superior to prior art in both effectiveness and efficiency. Specifically, we reduce the accuracy gap between the pruned and original networks from 0.9% to 0.7% with 8x reduction in time needed for meta-learning, i.e., from 1 hour down to 7 minutes. To this end, we demonstrate the effectiveness of our algorithm using ResNet and MobileNetV2 networks under CIFAR-10, ImageNet, and Bird-200 datasets.