NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
Open accessThe DOI matches its Crossref record; 49 of the 51 references it cites were found in a registry or an index.
Abstract
Deep neural networks (DNNs) have begun to have a pervasive impact on various applications of machine learning. However, the problem of finding an optimal DNN architecture for large applications is challenging. Common approaches go for deeper and larger DNN architectures but may incur substantial redundancy. To address these problems, we introduce a network growth algorithm that complements network pruning to learn both weights and compact DNN architectures during training. We propose a DNN synthesis tool (NeST) that combines both methods to automate the generation of compact and accurate DNNs. NeST starts with a randomly initialized sparse network called the seed architecture. It iteratively tunes the architecture with gradient-based growth and magnitude-based pruning of neurons and connections. Our experimental results show that NeST yields accurate, yet very compact DNNs, with a wide range of seed architecture selection. For the LeNet-300-100 (LeNet-5) architecture, we reduce network parameters by 70.2× (74.3×) and floating-point operations (FLOPs) by 79.4× (43.7×). For the AlexNet, VGG-16, and ResNet-50 architectures, we reduce network parameters (FLOPs) by 15.7× (4.6×), 33.2× (8.9×), and 4.1× (2.1×) respectively. NeST's grow-and-prune paradigm delivers significant additional parameter and FLOPs reduction relative to pruning-only methods.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The off-the-shelf hardware and software cannot efficiently execute those compressed formats, so specialized hardware and software libraries are required to execute sparsified DNN models [83], [84].”
From Bringing ai to edge: from deep learning’s perspective (2022) · cites this paper as [84]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 18×
“7 shows the area-of-interest found by the layer-1 kernels in LeNet-5 when applied to MNIST.”
BackgroundMethodInfluentialDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“Thus, it has been widely applied to large DNNs [30].”
BackgroundSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
(2017) · Cited by 11,625
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893
Learning Transferable Architectures for Scalable Image Recognition
Zoph, B., Vasudevan, V., Shlens, J., & Le, Q. V. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00907 · Cited by 7,831
Reading digits in natural images with unsupervised feature learning
Netzer, Y. (2024) · doi:10.57702/e7wwo0zk · Cited by 4,149
Neural Architecture Search with Reinforcement Learning
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 3,974
Evolving Neural Networks through Augmenting Topologies
Stanley, K. O., & Miikkulainen, R. (2002) · Evolutionary Computation · doi:10.1162/106365602320169811 · Cited by 3,258
Pruning Filters for Efficient ConvNets
Li, H., Kadav, A., Durdanovic, I., Samet, H., & Graf, H. P. (2016) · arXiv · doi:10.48550/arxiv.1608.08710 · Cited by 2,928
Empirical Evaluation of Rectified Activations in Convolutional Network
Xu, B., Wang, N., Chen, T., & Li, M. (2015) · arXiv · doi:10.48550/arxiv.1505.00853 · Cited by 2,264 · cited 1×
“This is because Leaky ReLU alleviates the ‘dying ReLU’ problem (i.e., when an inactive ReLU neuron is stuck at a perpetually inactive state since no gradients flow backward through it) and leads to better performance [54].”
BackgroundEIE: efficient inference engine on compressed deep neural network
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., & Dally, W. J. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001163 · Cited by 1,937
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
Luo, J.-H., Wu, J., & Lin, W. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.541 · Cited by 1,832
Learning both Weights and Connections for Efficient Neural Networks
Han, S., Pool, J., Tran, J., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1506.02626 · Cited by 1,481
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
Denton, R., Zaremba, W., Bruna, J., LeCun, Y., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1404.0736 · Cited by 1,414
Compressing Deep Convolutional Networks using Vector Quantization
Gong, Y., Liu, L., Yang, M., & Bourdev, L. D. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6115 · Cited by 925
One weird trick for parallelizing convolutional neural networks
Krizhevsky, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1404.5997 · Cited by 919
Miikkulainen, R., Liang, J., Meyerson, E., Rawal, A., Fink, D., Francon, O., Raju, B., Shahrzad, H., Navruzyan, A., Duffy, N., et al. (2019) · Artificial Intelligence in the Age of Neural Networks and Brain Computing · doi:10.1016/b978-0-12-815480-9.00015-3 · Cited by 760
Selection of Intrinsic Horizontal Connections in the Visual Cortex by Correlated Neuronal Activity
Löwel, S., & Singer, W. (1992) · Science · doi:10.1126/science.1372754 · Cited by 707
Sparse Convolutional Neural Networks
Liu, B., Wang, M., Foroosh, H., Tappen, M., & Penksy, M. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298681 · Cited by 680
Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
Hu, H., Peng, R., Tai, Y., & Tang, C. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.03250 · Cited by 668
Data-free Parameter Pruning for Deep Neural Networks
Srinivas, S., & Babu, R. V. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.31 · Cited by 505
Large-Scale Evolution of Image Classifiers
Real, E., Moore, S., Selle, A. P., Saxena, S., Suematsu, Y. I. L., Tan, J., Le, Q. V., & Kurakin, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.01041 · Cited by 466
Learning in feedforward layered networks: the tiling algorithm
Mezard, M., & Nadal, J.-P. (1989) · Journal of Physics A: Mathematical and General · doi:10.1088/0305-4470/22/12/019 · Cited by 426
Dynamic node creation in backpropagation networks
ASH, T. (1989) · Connection Science · doi:10.1080/09540098908915647 · Cited by 415
Learning Structured Sparsity in Deep Neural Networks
Wen, W. X., Wu, C., Wang, Y., Chen, Y., & Li, H. H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.03665 · Cited by 402
Designing Neural Network Architectures using Reinforcement Learning
Baker, B., Gupta, O., Naik, N., & Raskar, R. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02167 · Cited by 372
Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon
Dong, X., Chen, S., & Pan, S. J. (2017) · arXiv · doi:10.48550/arxiv.1705.07565 · Cited by 339
(1996) · Cited by 315
Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
Mao, H., Han, S., Pool, J., Li, W., Liu, X., Wang, Y., & Dally, W. J. (2017) · arXiv · doi:10.48550/arxiv.1705.08922 · Cited by 219 · cited 1×
“8 (2:0 ) Net pruning (ResNet-50) [39] Prune +0.”
Yang, Z., Moczulski, M., Denil, M., De Freitas, N., Song, L., & Wang, Z. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.173 · Cited by 215 · cited 1×
“0 (1:5 ) Fastfood-16-AD [35] +0.”
Sparsifying Neural Network Connections for Face Recognition
Sun, Y., Wang, X., & Tang, X. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.525 · Cited by 151
Dynamic Network Surgery for Efficient DNNs
Guo, Y., Yao, A., & Chen, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.04493 · Cited by 137
Exploiting sparseness in deep neural networks for large vocabulary speech recognition
Yu, D., Seide, F., Li, G., & Deng, L. (2012) · 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2012.6288897 · Cited by 137
DeepArchitect: Automatically Designing and Training Deep Architectures
Negrinho, R. M. P., & Gordon, G. J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.08792 · Cited by 126
Memory Bounded Deep Convolutional Networks
Collins, M. D., & Kohli, P. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.1442 · Cited by 112
The neurological development of the child with the educational enrichment in mind
Leisman, G., Mualem, R., & Mughrabi, S. K. (2015) · Psicología Educativa · doi:10.1016/j.pse.2015.08.006 · Cited by 67
DSD: Regularizing Deep Neural Networks with Dense-Sparse-Dense Training Flow.Preprint
Han, S., Pool, J., Narang, S., Mao, H., Tang, S., Elsen, E., Catanzaro, B., Tran, J. J., & Dally, W. J. (2016) · arXiv (Cornell University) · Cited by 64
Compact Deep Convolutional Neural Networks With Coarse Pruning
Anwar, S., & Sung, W. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.09639 · Cited by 29
Cited by
Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey
Deng, B. L., Li, G., Han, S., Shi, L., & Xie, Y. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.2976475 · Cited by 996
“Given a small seed network, NeST [217] combines the gradient-aware growing and magnitude-aware pruning, which can be used on both weights and neurons.”
MethodA Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations
Cheng, H., Zhang, M., & Shi, J. Q. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3447085 · Cited by 497
A Systematic DNN Weight Pruning Framework Using Alternating Direction Method of Multipliers
Zhang, T., Ye, S., Zhang, K., Tang, J., Wen, W., Fardad, M., & Wang, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01237-3_12 · Cited by 473
Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review
Shuvo, M. M. H., Islam, S. K., Cheng, J., & Morshed, B. I. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3226481 · Cited by 436
“For example, in [95], in each iteration, a small percentage of the least important weights based on a predefined threshold are removed from every layer, and the models are retrained to evaluate the performance.”
BackgroundHoefler, T., Alistarh, D., Ben-Nun, T., Dryden, N., & Peste, A. (2021) · ETH Zurich · doi:10.3929/ethz-b-000519202 · Cited by 423
Metadata
- Authors
- Dai, X., Yin, H., & Jha, N. K.
- Affiliations
- Princeton University (US)
- Venue
- IEEE Transactions on Computers
- Published
- 2019-10-01
- Volume
- 68
- Issue
- 10
- Pages
- 1487-1497
- ISSN
- 0018-9340 (ISSN-L)
- 1557-9956
- 2326-3814
- OpenAlex
- W2963319203
- Cited by
- 233
- References
- 51
- Citations by year
- 2026: 8 · 2025: 18 · 2024: 15 · 2023: 25 · 2022: 38 · 2021: 54 · 2020: 45 · 2019: 20
- FWCI
- 17.36
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Computers (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- US National Science Foundation (CNS-1617640)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- neural network synthesis, network pruning, network expansion, architecture search, compact neural networks, magnitude-based pruning, parameter reduction, FLOPs reduction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.