# Pruning by Active Attention Manipulation

arXiv: https://arxiv.org/abs/2210.11114 · HTML: https://mlsanity.com/paper/2210.11114/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1808.06866/) (2018)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [Neural Architecture Search without Training](https://mlsanity.com/paper/2006.04647/) (2020)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [NISP: Pruning Networks using Neuron Importance Score Propagation](https://mlsanity.com/paper/1711.05908/) (2017)
- [Discrimination-aware Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/1810.11809/) (2018)
- [Structured Pruning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.08571/) (2015)
- [Towards Optimal Structured CNN Pruning via Generative Adversarial Learning](https://mlsanity.com/paper/1903.09291/) (2019)
- [Provable Filter Pruning for Efficient Neural Networks](https://mlsanity.com/paper/1911.07412/) (2019)
- [SCOP: Scientific Control for Reliable Neural Network Pruning](https://mlsanity.com/paper/2010.10732/) (2020)
- [CHIP: CHannel Independence-based Pruning for Compact Neural Networks](https://mlsanity.com/paper/2110.13981/) (2021)
- [Residual Connections Encourage Iterative Inference](https://mlsanity.com/paper/1710.04773/) (2017)
- [AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference](https://mlsanity.com/paper/1805.08941/) (2018)
- [AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks](https://mlsanity.com/paper/2106.12379/) (2021)
- [Learning Filter Basis for Convolutional Neural Network Compression](https://mlsanity.com/paper/1908.08932/) (2019)
- [Highway and Residual Networks learn Unrolled Iterative Estimation](https://mlsanity.com/paper/1612.07771/) (2016)

## Abstract (arXiv)

Filter pruning of a CNN is typically achieved by applying discrete masks on the CNN's filter weights or activation maps, post-training. Here, we present a new filter-importance-scoring concept named pruning by active attention manipulation (PAAM), that sparsifies the CNN's set of filters through a particular attention mechanism, during-training. PAAM learns analog filter scores from the filter weights by optimizing a cost function regularized by an additive term in the scores. As the filters are not independent, we use attention to dynamically learn their correlations. Moreover, by training the pruning scores of all layers simultaneously, PAAM can account for layer inter-dependencies, which is essential to finding a performant sparse sub-network. PAAM can also train and generate a pruned network from scratch in a straightforward, one-stage training process without requiring a pre-trained network. Finally, PAAM does not need layer-specific hyperparameters and pre-defined layer budgets, since it can implicitly determine the appropriate number of filters in each layer. Our experimental results on different network architectures suggest that PAAM outperforms state-of-the-art structured-pruning methods (SOTA). On CIFAR-10 dataset, without requiring a pre-trained baseline network, we obtain 1.02% and 1.19% accuracy gain and 52.3% and 54% parameters reduction, on ResNet56 and ResNet110, respectively. Similarly, on the ImageNet dataset, PAAM achieves 1.06% accuracy gain while pruning 51.1% of the parameters on ResNet50. For Cifar-10, this is better than the SOTA with a margin of 9.5% and 6.6%, respectively, and on ImageNet with a margin of 11%.