Abstract
In recent years, there has been a lot of studies in neural architecture search (NAS) in the field of deep learning. Among them, the cell-based search method, such as [23, 27, 32, 36], is one of the most popular and widely discussed topics, which usually stacks less cells in search process and more in evaluation. Although this method can reduce the resource consumption in the process of search, the difference in the number of cells may inevitably cause a certain degree of redundancy in network evaluation. In order to mitigate the computational cost, we propose a novel algorithm called Edge-Wise One-Level Global Pruning (EOG-Pruning). The proposed approach can prune out weak edges from the cell-based network generated by NAS globally, by introducing an edge factor to represent the importance of each edge, which can not only greatly improve the inference speed of the model with reducing the number of edges, but also promote the model accuracy. Experimental results show that networks pruned by EOG-Pruning achieve significant improvement in accuracy and speedup rate on CPU in common with 50% pruning rate on CIFAR. Specifically, we reduced the test error rate by 1.58% and 1.34% on CIFAR-100 for DARTS (2nd-order) and PC-DARTS.
Supported by Beijing Natural Science Foundation (4202063), Fundamental Research Funds for the Central Universities (2020JBM020), Research Founding of Electro-Optical Information Security Control Laboratory, National Key Research and Development Program of China under Grant 2019YFB2204200, BJTU-Kuaishou Research Grant.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baker, B., Gupta, O., Naik, N., Raskar, R.: Designing neural network architectures using reinforcement learning. In: Submitted to International Conference on Learning Representations (2016)
Bergstra, J., Bardenet, R., Bengio, Y., Kégl, B.: Algorithms for Hyper-parameter optimization. In: Proceedings of the 24th International Conference on Neural Information Processing Systems, pp. 2546–2554. NIPS 2011, Curran Associates Inc., Red Hook, NY, USA (2011), event-place: Granada, Spain
Bi, K., Hu, C., Xie, L., Chen, X., Wei, L., Tian, Q.: Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters. arXiv e-prints arXiv:1910.11831 (2019)
Bi, K., Xie, L., Chen, X., Wei, L., Tian, Q.: GOLD-NAS: Gradual, One-Level, Differentiable. arXiv e-prints arXiv:2007.03331 (2020)
Cai, H., Zhu, L., Han, S.: ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. arXiv e-prints arXiv:1812.00332
Chen, X., Xie, L., Wu, J., Tian, Q.: Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation. arXiv e-prints arXiv:1904.12760 (2019)
Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation strategies from data. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 113–123. IEEE, Long Beach, CA, USA, June 2019. https://doi.org/10.1109/CVPR.2019.00020, https://ieeexplore.ieee.org/document/8953317/
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009). https://doi.org/10.1109/CVPR.2009.5206848
DeVries, T., Taylor, G.W.: Improved Regularization of Convolutional Neural Networks with Cutout. arXiv e-prints arXiv:1708.04552 (2017)
Ghiasi, G., Lin, T.Y., Pang, R., Le, Q.V.: NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection. arXiv e-prints arXiv:1904.07392, April 2019
Goyal, P., et al.: Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour. arXiv e-prints arXiv:1706.02677 (2017)
Han, S., Mao, H., Dally, W.J.: Deep compression: compressing deep neural networks with pruning. ICLR, trained quantization and huffman coding (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1398–1406 (2017). https://doi.org/10.1109/ICCV.2017.155
Huang, G., Liu, Z., Maaten, L.V.D., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269 (2017). https://doi.org/10.1109/CVPR.2017.243
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Handb. Syst. Autoimmune Dis. 1(4) (2009)
Larsson, G., Maire, M., Shakhnarovich, G.: Fractalnet: Ultra-deep neural networks without residuals. In: ICLR (2017)
LeCun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems 2, pp. 598–605. Morgan-Kaufmann (1990). http://papers.nips.cc/paper/250-optimal-brain-damage.pdf
Li, H., Kadav, A., Durdanovic, I., Samet, H., Graf, H.P.: Pruning filters for efficient ConvNets. In: International Conference on Learning Representations (ICLR) (2016)
Li, K., Malik, J.: Learning to Optimize. arXiv e-prints arXiv:1606.01885 (2016)
Li, L., Talwalkar, A.: Random Search and Reproducibility for Neural Architecture Search. arXiv e-prints arXiv:1902.07638 (2019)
Liu, C., et al.: Progressive Neural Architecture Search. arXiv e-prints arXiv:1712.00559 (2017)
Liu, H., Simonyan, K., Yang, Y.: DARTS: Differentiable Architecture Search. arXiv e-prints arXiv:1806.09055 (2018)
Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)
Luo, J.H., Wu, J., Lin, W.: ThiNet: a filter level pruning method for deep neural network compression. In: ICCV, pp. 5068–5076 (2017). https://doi.org/10.1109/ICCV.2017.541
Pham, H., Guan, M.Y., Zoph, B., Le, Q.V., Dean, J.: Efficient neural architecture search via parameter sharing. In: ICML, pp. 4092–4101 (2018). http://proceedings.mlr.press/v80/pham18a.html
Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: AAAI, pp. 4780–4789 (2019). https://doi.org/10.1609/aaai.v33i01.33014780
Shin*, R., Packer*, C., Song, D.: Differentiable neural network architecture search. In: In International Conference on Learning Representationss-Workshops (2018). https://openreview.net/forum?id=BJ-MRKkwG
Suganuma, M., Shirakawa, S., Nagao, T.: A genetic programming approach to designing convolutional neural network architectures. In: IJCAI, pp. 5369–5373 (2018). https://doi.org/10.24963/ijcai.2018/755
Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015). https://doi.org/10.1109/CVPR.2015.7298594
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR, pp. 2818–2826 (2016). https://doi.org/10.1109/CVPR.2016.308
Xie, L., Yuille, A.: Genetic CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1388–1397 (2017). https://doi.org/10.1109/ICCV.2017.154
Xu, Y., et al.: PC-DARTS: partial channel connections for memory-efficient architecture search. In: Submitted to International Conference on Learning Representations (2020). https://openreview.net/forum?id=BJlS634tPr
Yao, L., Xu, H., Zhang, W., Liang, X., Li, Z.: SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection. arXiv e-prints arXiv:1911.09929 (2019)
Zoph, B., Le, Q.V.: Neural Architecture Search with Reinforcement Learning. arXiv e-prints arXiv:1611.01578 (2016)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Feng, Q., Xu, K., Li, Y., Sun, Y., Wang, D. (2021). Edge-Wise One-Level Global Pruning on NAS Generated Networks. In: Ma, H., et al. Pattern Recognition and Computer Vision. PRCV 2021. Lecture Notes in Computer Science(), vol 13022. Springer, Cham. https://doi.org/10.1007/978-3-030-88013-2_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-88013-2_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88012-5
Online ISBN: 978-3-030-88013-2
eBook Packages: Computer ScienceComputer Science (R0)