Beyond Network Pruning: a Joint Search-and-Training Approach


Xiaotong Lu1   Han Huang1   Weisheng Dong1*    Xin Li2    Guangming Shi1

1School of Artificial Intelligence, Xidian University               2West Virginia University




Figure 1. Overview of our joint search-and-training approach. The ’sampler’ searches for compact sub-networks from the target network, while the ’updater’ maps the trained sub-networks back to the target network.The best performing sub-network will be further fine-tuned as the final output.




Network pruning has been proposed as a remedy for alleviating the over-parameterization problem of deep neural networks. However, its value has been recently challenged especially from the perspective of neural architecture search (NAS). We challenge the conventional wisdom of pruning after-training by proposing a joint search-and-training approach that directly learns a compact network from the scratch. By treating pruning as a search strategy, we present two new insights in this paper: 1) it is possible to expand the search space of networking pruning by associating each filter with a learnable weight; 2) joint search-and-training can be conducted iteratively to maximize the learning effificiency. More specifically, we propose a coarse-to-fine tuning strategy to iteratively sample and update compact sub-network to approximate the target network. The weights associated with network fifilters will be accordingly updated by joint search-and-training to reflect learned knowledge in NAS space. Moreover, we introduce strategies of random perturbation (inspired by Monte Carlo) and flexible thresholding (inspired by Reinforcement Learning) to adjust the weight and size of each layer. Extensive experiments on ResNet and VGGNet demonstrate the superior performance of our proposed method on popular datasets including CIFAR10, CIFAR100 and ImageNet.






                                        IJCAI 2020                                 


Lu X, Huang H, Dong W, et al. Beyond network pruning: a joint search-and-training approach[C]//International Joint Conference on Artificial Intelligence. 2020.





  title={Beyond network pruning: a joint search-and-training approach},

  author={Lu, Xiaotong and Huang, Han and Dong, Weisheng and Li, Xin and Shi, Guangming},

  booktitle={International Joint Conference on Artificial Intelligence},







CIFAR Results:






ImageNet Results:





[1] José MBioucas-Dias and Mário ATFigueiredo. Anew twist: Two-step iterative shrinkage/thresholding algorithms for image restoration. IEEE Transactions on Image processing, 16(12):2992–3004, 2007.

[2] Xin Yuan. Generalized alternating projection based total variation minimization for compressive sensing. In 2016 IEEE International Conference on Image Processing (ICIP), pages 2539–2543. IEEE, 2016.

[3] Yang Liu, Xin Yuan, Jinli Suo, David J Brady, and Qionghai Dai. Rank minimization for snapshot compressive imaging. IEEE transactions on pattern analysis and machine intelligence, 41(12):2990–3006, 2018.

[4] Xin Miao, Xin Yuan, Yunchen Pu, and Vassilis Athitsos. lambda-net: Reconstruct hyperspectral images from a snapshot measurement. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 4058–4068. IEEE, 2019.

[5] Lizhi Wang, Chen Sun, Ying Fu, Min H Kim, and Hua Huang. Hyperspectral image reconstruction using a deep spatial-spectralprior. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8032–8041, 2019.

[6] Lizhi Wang, Chen Sun, Maoqing Zhang, Ying Fu, and Hua Huang. Dnu: Deep non-local unrolling for computational spectral imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1661–1671, 2020.

[7] Ziyi Meng, Jiawei Ma, and Xin Yuan. End-to-end low cost compressive spectral imaging with spatial-spectral self-attention. In European Conference on Computer Vision, pages 187–204. Springer, 2020.





Xiaotong Lu, Email:

Han Huang,

Weisheng Dong, Email:

Xin Li, Email:

Guangming Shi, Email: