ABSTRACT
Sparse neural networks have been proven to generate efficient and better runtimes when compared to dense neural networks. Acceleration in runtime is better achieved with structured sparsity. However, generating an efficient sparsity structure to maintain both runtime and accuracy is a challenging task. In this paper, we implement the RBGP4 sparsity pattern derived from the Ramanujan Bipartite Graph Product (RBGP) framework on various Computer Vision tasks and test how well it performs w.r.t accuracy and runtime. Using this approach, we generate structured sparse neural networks which has multiple levels of block sparsity that generates good connectivity due to the presence of Ramanujan bipartite graphs. We benchmark our approach on Semantic Segmentation and Pose Estimation tasks on an edge device (Jetson Nano 2GB) as well as server (V100) GPUs. We compare the results obtained for RBGP4 sparsity pattern with the unstructured and block sparsity patterns. When compared to sparsity patterns like unstructured and block, we obtained significant speedups while maintaining accuracy.
- Sajid Anwar, Kyuyeon Hwang, and Wonyong Sung. 2017. Structured Pruning of Deep Convolutional Neural Networks. J. Emerg. Technol. Comput. Syst. 13, 3, Article 32 (feb 2017), 18 pages. https://doi.org/10.1145/3005348Google ScholarDigital Library
- Junyi Chai, Hao Zeng, Anming Li, and Eric W.T. Ngai. 2021. Deep learning in computer vision: A critical review of emerging techniques and application scenarios. Machine Learning with Applications 6 (2021), 100134. https://doi.org/10.1016/j.mlwa.2021.100134Google ScholarCross Ref
- Yu Cheng, Duo Wang, Pan Zhou, and Tao Zhang. 2018. Model Compression and Acceleration for Deep Neural Networks: The Principles, Progress, and Challenges. IEEE Signal Processing Magazine 35, 1 (2018), 126–136. https://doi.org/10.1109/MSP.2017.2765695Google ScholarCross Ref
- Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan M. Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cuDNN: Efficient Primitives for Deep Learning. ArXiv abs/1410.0759(2014).Google Scholar
- Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele. 2016. The Cityscapes Dataset for Semantic Urban Scene Understanding. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Google ScholarCross Ref
- Jonathan Frankle and Michael Carbin. 2018. The Lottery Ticket Hypothesis: Training Pruned Neural Networks. CoRR abs/1803.03635(2018). arXiv:1803.03635http://arxiv.org/abs/1803.03635Google Scholar
- Gousia Habib and Shaima Qureshi. 2022. Optimization and acceleration of convolutional neural networks: A survey. Journal of King Saud University - Computer and Information Sciences 34, 7(2022), 4244–4268. https://doi.org/10.1016/j.jksuci.2020.10.004Google ScholarDigital Library
- Song Han, Jeff Pool, John Tran, and William J. Dally. 2015. Learning Both Weights and Connections for Efficient Neural Networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1 (Montreal, Canada) (NIPS’15). MIT Press, Cambridge, MA, USA, 1135–1143.Google Scholar
- Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized Neural Networks. In Advances in Neural Information Processing Systems, D. Lee, M. Sugiyama, U. Luxburg, I. Guyon, and R. Garnett (Eds.). Vol. 29. Curran Associates, Inc.https://proceedings.neurips.cc/paper/2016/file/d8330f857a17c53d217014ee776bfd50-Paper.pdfGoogle Scholar
- François Lagunas, Ella Charlaix, Victor Sanh, and Alexander Rush. 2021. Block Pruning For Faster Transformers. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 10619–10629. https://doi.org/10.18653/v1/2021.emnlp-main.829Google ScholarCross Ref
- Yann LeCun, John Denker, and Sara Solla. 1989. Optimal Brain Damage. In Advances in Neural Information Processing Systems, D. Touretzky (Ed.). Vol. 2. Morgan-Kaufmann. https://proceedings.neurips.cc/paper/1989/file/6c9882bbac1c7093bd25041881277658-Paper.pdfGoogle Scholar
- Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2017. Pruning Filters for Efficient ConvNets. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=rJqFGTslgGoogle Scholar
- Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Computer Vision – ECCV 2014, David Fleet, Tomas Pajdla, Bernt Schiele, and Tinne Tuytelaars (Eds.). Springer International Publishing, Cham, 740–755.Google ScholarCross Ref
- Baoyuan Liu, Min Wang, Hassan Foroosh, Marshall Tappen, and Marianna Penksy. 2015. Sparse Convolutional Neural Networks. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 806–814. https://doi.org/10.1109/CVPR.2015.7298681Google Scholar
- Jiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng, Changhu Wang, and Jiashi Feng. 2020. Improving Convolutional Networks with Self-Calibrated Convolutions. In IEEE CVPR.Google Scholar
- Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, and Saining Xie. 2022. A ConvNet for the 2020s. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11976–11986.Google ScholarCross Ref
- Gaurav Menghani. 2021. Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better. CoRR abs/2106.08962(2021). arXiv:2106.08962https://arxiv.org/abs/2106.08962Google Scholar
- Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, and Jan Kautz. 2017. Pruning Convolutional Neural Networks for Resource Efficient Inference. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=SJGCiw5glGoogle Scholar
- Ameya Prabhu, Girish Varma, and Anoop Namboodiri. 2018. Deep Expander Networks: Efficient Deep Networks from Graph Theory. In Proceedings of the European Conference on Computer Vision (ECCV).Google ScholarDigital Library
- Tara N. Sainath, Brian Kingsbury, Vikas Sindhwani, Ebru Arisoy, and Bhuvana Ramabhadran. 2013. Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (2013), 6655–6659.Google ScholarCross Ref
- Cheng-Hao Tu, Jia-Hong Lee, Yi-Ming Chan, and Chu-Song Chen. 2020. Pruning Depthwise Separable Convolutions for MobileNet Compression. In 2020 International Joint Conference on Neural Networks (IJCNN). 1–8. https://doi.org/10.1109/IJCNN48605.2020.9207259Google Scholar
- Dharma Teja Vooturi, Girish Varma, and Kishore Kothapalli. [n. d.]. Ramanujan bipartite graph products for efficient block sparse neural networks. Concurrency and Computation: Practice and Experience n/a, n/a([n. d.]), e6363. https://doi.org/10.1002/cpe.6363 arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/cpe.6363Google Scholar
- Wei Wen, Chunpeng Wu, Yandan Wang, Yiran Chen, and Hai Li. 2016. Learning Structured Sparsity in Deep Neural Networks. In Proceedings of the 30th International Conference on Neural Information Processing Systems (Barcelona, Spain) (NIPS’16). Curran Associates Inc., Red Hook, NY, USA, 2082–2090.Google ScholarDigital Library
- Bin Xiao, Haiping Wu, and Yichen Wei. 2018. Simple Baselines for Human Pose Estimation and Tracking. In Proceedings of the European Conference on Computer Vision (ECCV).Google ScholarDigital Library
- Xin Yuan, Pedro Henrique Pamplona Savarese, and Michael Maire. 2021. Growing Efficient Deep Networks by Structured Continuous Sparsification. In International Conference on Learning Representations. https://openreview.net/forum?id=wb3wxCObbRTGoogle Scholar
- Michael Zhu and Suyog Gupta. 2017. To prune, or not to prune: exploring the efficacy of pruning for model compression. https://doi.org/10.48550/ARXIV.1710.01878Google Scholar
- Mingjian Zhu, Kai Han, Yehui Tang, and Yunhe Wang. 2021. Visual Transformer Pruning. CoRR abs/2104.08500(2021). arXiv:2104.08500https://arxiv.org/abs/2104.08500Google Scholar
Recommendations
Accelerating the LOBPCG method on GPUs using a blocked sparse matrix vector product
HPC '15: Proceedings of the Symposium on High Performance ComputingThis paper presents a heterogeneous CPU-GPU implementation for a sparse iterative eigensolver -- the Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG). For the key routine generating the Krylov search spaces via the product of a sparse ...
Ramanujan coverings of graphs
STOC '16: Proceedings of the forty-eighth annual ACM symposium on Theory of ComputingLet G be a finite connected graph, and let ρ be the spectral radius of its universal cover. For example, if G is k-regular then ρ=2√k−1. We show that for every r, there is an r-covering (a.k.a. an r-lift) of G where all the new eigenvalues are bounded ...
Accelerating the Explicitly Restarted Arnoldi Method with GPUs Using an Autotuned Matrix Vector Product
† Special Section: 2010 Copper Mountain ConferenceThis paper presents a parallelized hybrid single-vector Arnoldi algorithm for computing approximations to eigenpairs of a nonsymmetric matrix. We are interested in the use of accelerators and multicore units to speed up the Arnoldi process. The main ...
Comments