{"type":"ScholarlyArticle","title":"On the Channel Pruning using Graph Convolution Network for Convolutional Neural Network Acceleration","authors":[{"name":"Di Jiang","slug":"di-jiang","given":"Di","family":"Jiang","affiliation":"College of Electrical Engineering , Zhejiang University , 310027 , Hangzhou China"},{"name":"Yuan Cao","slug":"yuan-cao","given":"Yuan","family":"Cao","affiliation":"College of Electrical Engineering , Zhejiang University , 310027 , Hangzhou China"},{"name":"Qiang Yang","slug":"qiang-yang","given":"Qiang","family":"Yang","affiliation":"College of Electrical Engineering , Zhejiang University , 310027 , Hangzhou China"}],"abstract":"Network pruning is considered efficient for sparsification and acceleration of Convolutional Neural Network (CNN) based models that can be adopted in re-source-constrained environments. Inspired by two popular pruning criteria, i.e. magnitude and similarity, this paper proposes a novel structural pruning method based on Graph Convolution Network (GCN) to further promote compression performance. The channel features are firstly extracted by Global Average Pooling (GAP) from a batch of samples, and a graph model for each layer is generated based on the similarity of features. A set of agents for individual CNN layers are implemented by GCN and utilized to synthesize comprehensive channel information and determine the pruning scheme for the overall CNN model. The training process of each agent is carried out using Reinforcement Learning (RL) to ensure their convergence and adaptability to various network architectures. The proposed solution is assessed based on a range of image classification datasets i.e., CIFAR and Tiny-ImageNet. The numerical results indicate that the proposed pruning method outperforms the pure magnitude-based or similarity-based pruning solutions and other SOTA methods (e.g., HRank and SCP). For example, the proposed method can prune VGG16 by removing 93% of the model parameters without any accuracy reduction in the CIFAR10 dataset.","doi":"10.24963/ijcai.2022/431","url":"https://ijcai.org/proceedings/2022/431","pdf":"https://ijcai.org/proceedings/2022/0431.pdf","markdown":"https://ijcai.org/proceedings/2022/431.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/431","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":431,"pages":{"first":3107,"last":3113},"keywords":["Machine Learning: Learning Sparse Models","Machine Learning: Learning Graphical Models","Machine Learning: Classification","Machine Learning: Deep Reinforcement Learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987070","length_sec":74,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985213","length_sec":572,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Hao Li, 2017] Asim Kadav Hao Li, Igor Durdanovic, Hanan Samet, Hans Peter Graf. Pruning Filters for Efficient ConvNets. In International Conference on Learning Representations, Toulon, France, April 24 -26, 2017.","title":"Pruning Filters for Efficient ConvNets","authors":"Asim Kadav, Hao Li, Igor Durdanovic, Hanan Samet, Hans Peter Graf","year":"2017","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Hu et al., 2016] Hengyuan Hu, Rui Peng, Yu-Wing Tai, et al. Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250, 2016.","title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","authors":"Hengyuan Hu, Rui Peng, Yu-Wing Tai","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Liu et al., 2017] Zhuang Liu, Jianguo Li, Zhiqiang Shen, et al. Learning efficient convolutional networks through network slimming. In International Conference on Computer Vision, 2736-2744, 2017.","title":"Learning efficient convolutional networks through network slimming","authors":"Zhuang Liu, Jianguo Li, Zhiqiang Shen","year":"2017","venue":"International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Lei et al., 2017] Wang Lei, Huawei Chen and Yixuan Wu. Compressing Deep Convolutional Networks Using K- means Based on Weights Distribution. In International Conference on Intelligent Information Processing, Article 10, Bangkok, Thailand, 2017.","title":"Compressing Deep Convolutional Networks Using Kmeans Based on Weights Distribution","authors":"Wang Lei, Huawei Chen, Yixuan Wu","year":"2017","venue":"International Conference on Intelligent Information Processing, Article 10","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ding et al., 2019] Xiaohan Ding, Guiguang Ding, Yuchen Guo, et al. Centripetal SGD for Pruning Very Deep Convolutional Networks With Complicated Structure. In Conference on Computer Vision and Pattern Recognition, 4938-4948, 15-20 June 2019.","title":"Centripetal SGD for Pruning Very Deep Convolutional Networks With Complicated Structure","authors":"Xiaohan Ding, Guiguang Ding, Yuchen Guo","year":"2019","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Wang et al., 2021] Zi Wang, Chengcheng Li and Xiangyang Wang. Convolutional neural network pruning with structural redundancy reduction. In Conference on Computer Vision and Pattern Recognition, 14913-14922, 2021.","title":"Convolutional neural network pruning with structural redundancy reduction","authors":"Zi Wang, Chengcheng Li, Xiangyang Wang","year":"2021","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Li et al., 2020] Hang Li, Chen Ma, Wei Xu, et al. Feature statistics guided efficient filter pruning. arXiv preprint arXiv:2005.12193, 2020.","title":"Feature statistics guided efficient filter pruning","authors":"Hang Li, Chen Ma, Wei Xu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2020/363"},{"position":8,"raw":"[He et al., 2018] Yang He, Guoliang Kang, Xuanyi Dong, et al. Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks. In International Joint Conference on Artificial Intelligence, Stockholm, Sweden, July 13-19 2018.","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","authors":"Yang He, Guoliang Kang, Xuanyi Dong","year":"2018","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/309"},{"position":9,"raw":"[Lee et al., 2021] Jaeho Lee, Sejun Park, Sangwoo Mo, et al. Layer-adaptive Sparsity for the Magnitude-based Pruning. In International Conference on Learning Representations, Vienna, Austria, May 04 2021.","title":"Layer-adaptive Sparsity for the Magnitude-based Pruning","authors":"Jaeho Lee, Sejun Park, Sangwoo Mo","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Zhao et al., 2019] Chenglong Zhao, Bingbing Ni, Jian Zhang, et al. Variational Convolutional Neural Network Pruning. In Conference on Computer Vision and Pattern Recognition, 2775-2784, 15-20 June 2019.","title":"Variational Convolutional Neural Network Pruning","authors":"Chenglong Zhao, Bingbing Ni, Jian Zhang","year":"2019","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[He et al., 2019] Yang He, Ping Liu, Ziwei Wang, et al. Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration. In Conference on Computer Vision and Pattern Recognition, 4335-4344, 15-20 June 2019.","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","authors":"Yang He, Ping Liu, Ziwei Wang","year":"2019","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Suau et al., 2018] Xavier Suau, Luca Zappella, Vinay Palakkode, et al. Principal filter analysis for guided network compression. arXiv preprint arXiv:1807.10585, 2018.","title":"Principal filter analysis for guided network compression","authors":"Xavier Suau, Luca Zappella, Vinay Palakkode","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lemaire et al., 2019] Carl Lemaire, Andrew Achkar and Pierre-Marc Jodoin. Structured pruning of neural networks with budget-aware regularization. In Conference on Computer Vision and Pattern Recognition, 9108-9116, 2019.","title":"Structured pruning of neural networks with budget-aware regularization","authors":"Carl Lemaire, Andrew Achkar, Pierre-Marc Jodoin","year":"2019","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[He et al., 2018] Yihui He, Ji Lin, Zhijian Liu, et al. Amc: Automl for model compression and acceleration on mobile devices. In European Conference on Computer Vision, 784-800, 2018.","title":"Amc: Automl for model compression and acceleration on mobile devices","authors":"Yihui He, Ji Lin, Zhijian Liu","year":"2018","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lin et al., 2019] Shaohui Lin, Rongrong Ji, Chenqian Yan, et al. Towards optimal structured cnn pruning via generative adversarial learning. In Conference on Computer Vision and Pattern Recognition, 2790-2799, 2019.","title":"Towards optimal structured cnn pruning via generative adversarial learning","authors":"Lin","year":"2019","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wu et al., 2018] Zuxuan Wu, Tushar Nagarajan, Abhishek Kumar, et al. Blockdrop: Dynamic inference paths in residual networks. In Conference on Computer Vision and Pattern Recognition, 8817-8826, 2018.","title":"Blockdrop: Dynamic inference paths in residual networks","authors":"Wu","year":"2018","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liu et al., 2020] Yabo Liu, Yi Liu and Cheng Yang. Modulation recognition with graph convolutional network. IEEE Wireless Communications Letters, 9:624- 627, 2020.","title":"Modulation recognition with graph convolutional network","authors":"Yabo Liu, Yi Liu, Cheng Yang","year":"2020","venue":"IEEE Wireless Communications Letters","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Zhuang and Ma, 2018] Chenyi Zhuang and Qiang Ma. Dual graph convolutional networks for graph-based semi- supervised classification. In Proceedings of the 2018 World Wide Web Conference, 499-508, 2018.","title":"Dual graph convolutional networks for graph-based semisupervised classification","authors":"Ma ; Zhuang, Chenyi Zhuang, Qiang Ma","year":"2018","venue":"Proceedings of the 2018 World Wide Web Conference","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Bruna et al., 2013] Joan Bruna, Wojciech Zaremba, Arthur Szlam, et al. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203, 2013.","title":"Spectral networks and locally connected networks on graphs","authors":"Joan Bruna, Wojciech Zaremba, Arthur Szlam","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Chen and Zhao, 2019] S. Chen and Q. Zhao. Shallowing Deep Networks: Layer-Wise Pruning Based on Feature Representations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41:3048-3056, 2019.","title":"Shallowing Deep Networks: Layer-Wise Pruning Based on Feature Representations","authors":"S Chen, Q Zhao","year":"2019","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ding et al., 2021] Xiaohan Ding, Tianxiang Hao, Jianchao Tan, et al. Lossless CNN Channel Pruning via Decoupling Remembering and Forgetting. In International Conference on Computer Vision, March 10, 2021.","title":"Lossless CNN Channel Pruning via Decoupling Remembering and Forgetting","authors":"Xiaohan Ding, Tianxiang Hao, Jianchao Tan","year":"2021","venue":"International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Chen et al., 2021] Tianyi Chen, Bo Ji, Tianyu Ding, et al. Only Train Once: A One-Shot Neural Network Training And Pruning Framework. arXiv preprint arXiv:2107.07467, 2021.","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","authors":"Tianyi Chen, Bo Ji, Tianyu Ding","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Krizhevsky and Hinton, 2009] Alex Krizhevsky and Geoffrey Hinton. Learning multiple layers of features from tiny images. Handbook of Systemic Autoimmune Diseases, 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky, Geoffrey Hinton","year":"2009","venue":"Handbook of Systemic Autoimmune Diseases","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, et al. Imagenet: A large-scale hierarchical image database. In Conference on Computer Vision and Pattern Recognition, 248-255, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher","year":"2009","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Simonyan and Zisserman, 2014] Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.","title":"Very deep convolutional networks for large-scale image recognition","authors":"Karen Simonyan, Andrew Zisserman","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, et al. Deep residual learning for image recognition. In Conference on Computer Vision and Pattern Recognition, 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren","year":"2016","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2021] Zidu Wang, Xuexin Liu, Long Huang, et al. Model Pruning Based on Quantified Similarity of Feature Maps. arXiv preprint arXiv:2105.06052, 2021.","title":"Model Pruning Based on Quantified Similarity of Feature Maps","authors":"Wang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[He et al., 2020] Yang He, Yuhang Ding, Ping Liu, et al. Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration. In Conference on Computer Vision and Pattern Recognition, 2006-2015, 13-19 June 2020.","title":"Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration","authors":"Yang He, Yuhang Ding, Ping Liu","year":"2006","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Lin et al., 2020] Mingbao Lin, Rongrong Ji, Yan Wang, et al. HRank: Filter Pruning Using High-Rank Feature Map. In Conference on Computer Vision and Pattern Recognition, 1526-1535, 13-19 June 2020.","title":"HRank: Filter Pruning Using High-Rank Feature Map","authors":"Lin","year":"2020","venue":"Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Kang and Han, 2020] Minsoo Kang and Bohyung Han. Operation-aware soft channel pruning using differentiable masks. In International Conference on Machine Learning, 5122-5131, 2020.","title":"Operation-aware soft channel pruning using differentiable masks","authors":"Minsoo Kang, Bohyung Han","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}