The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
Open accessAbstract
We present APQ, a novel design methodology for efficient deep learning deployment. Unlike previous methods that separately optimize the neural network architecture, pruning policy, and quantization policy, we design to optimize them in a joint manner. To deal with the larger design space it brings, we devise to train a quantization-aware accuracy predictor that is fed to the evolutionary search to select the best fit. Since directly training such a predictor requires time-consuming quantization data collection, we propose to use predictor-transfer technique to get the quantization-aware predictor: we first generate a large dataset of 〈NN architecture, ImageNet accuracy〉 pairs by sampling a pretrained unified once-for-all network and doing direct evaluation; then we use these data to train an accuracy predictor without quantization, followed by transferring its weights to train the quantization-aware predictor, which largely reduces the quantization data collection time. Extensive experiments on ImageNet show the benefits of this joint design methodology: the model searched by our method maintains the same level accuracy as ResNet34 8-bit model while saving 8× BitOps; we achieve 2×/1.3× latency/energy saving compared to MobileNetV2+HAQ [30, 36] while obtaining the same level accuracy; the marginal search cost ofjoint optimization for a new deployment scenario outperforms separate optimizations using ProxylessNAS+AMC+HAQ [5, 12, 36] by 2.3% accuracy while reducing orders of magnitude GPU hours and CO2emission with respect to the training cost.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00286 · Cited by 4,114
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
Energy and Policy Considerations for Deep Learning in NLP
Strubell, E., Ganesh, A., & McCallum, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1355 · Cited by 3,684
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00293 · Cited by 3,416
DARTS: Differentiable architecture search
Liu, H., Simonyan, K., & Yang, Y. (2018) · arXiv · doi:10.48550/arxiv.1806.09055 · Cited by 3,248
Learning Efficient Convolutional Networks through Network Slimming
Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., & Zhang, C. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.298 · Cited by 2,761
Self-citationChannel Pruning for Accelerating Very Deep Neural Networks
He, Y., Zhang, X., & Sun, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.155 · Cited by 2,647
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
Zhou, S., Wu, Y., Ni, Z., Zhou, X., Wen, H., & Zou, Y. (2016) · arXiv · doi:10.48550/arxiv.1606.06160 · Cited by 1,690
Once-for-All: Train One Network and Specialize it for Efficient Deployment
Cai, H., Gan, C., Wang, T., Zhang, Z., & Han, S. (2019) · arXiv · doi:10.48550/arxiv.1908.09791 · Cited by 845
Self-citationChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation
Dai, X., Zhang, P., Wu, B., Yin, H., Sun, F., Wang, Y., Dukhan, M., Hu, Y., Wu, Y., Jia, Y., et al. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.01166 · Cited by 279
Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
Wu, B., Wang, Y., Zhang, P., Tian, Y., Vajda, P., & Keutzer, K. (2018) · arXiv · doi:10.48550/arxiv.1812.00090 · Cited by 186
Research works printed but not linked: 32
- yang, 2018, Ne-tadapt: Platform-aware neural network adaptation for mobile applications, Lecture Notes in Computer Science
- 10.1109/ISCA.2018.00069 · DOI · Paper page
- 10.1109/CVPR.2019.01099 · DOI · Paper page
- wang, 0, Haq: Hardware-aware automated quantization, CVPR
- wang, 0, Learning to design circuits, NeurIPS 2018 Machine Learning for Systems Workshop
- wang, 0, Tts: Transferable transistor sizing with graph neural networks and reinforcement learning, ACM/IEEE 57th Design Automation Conference (DAC)
- han, 0, Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding, ICLRE
- zhang, 0, Sparch: Efficient architecture for sparse matrix multiplication, 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)
- han, 0, Learning both weights and connections for efficient neural network, NeurIPS
- he, 0, Amc: Automl for model compression and acceleration on mobile devices, ECCV
- hu, 2016, Network trimming A data-driven neuron pruning approach towards efficient deep architectures
- lin, 0, Runtime Neural Pruning, NIPS
- liu, 0, Progressive neural architecture search, ECCV
- liu, 0, Hierarchical representations for efficient architecture search, ICLRE
- rastegari, 0, XNOR-Net - ImageNet Classification Using Binary Convolutional Neural Networks, ECCV
- cai, 0, Path-level network transformation for efficient architecture search, ICML
- 10.1109/ACCESS.2015.2494536 · DOI · Paper page
- courbariaux, 2016, Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or ?1, ArXiv
- 10.1609/aaai.v33i01.33014780 · DOI · Paper page
- cai, 0, ProxylessNAS: Direct neural architecture search on target task and hardware, ICLRE
- guo, 2019, Single path one-shot neural architecture search with uniform sampling
- cai, 0, Efficient architecture search by network transformation, AAAI
- han, 2019, Design automation for efficient deep learning computing
- anwar, 2016, Compact deep convolutional neural networks with coarse pruning
- 10.1109/CVPR.2018.00907 · DOI · Paper page
- 10.1109/ICCV.2019.00339 · DOI · Paper page
- mao, 0, Park: An open platform for learning-augmented computer systems, Advances in neural information processing systems, 2490
- 10.1109/CVPR.2018.00982 · DOI
- luo, 0, Neural architecture optimization, NeurIPS
- 10.1109/HPCA.2018.00067 · DOI · Paper page
- zhu, 0, Trained ternary quantization, ICLRE
- molchanov, 2016, Pruning convolutional neural networks for resource efficient inference
Cited by
AutoML: A survey of the state-of-the-art
He, X., Zhao, K., & Chu, X. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106622 · Cited by 1,691
A Survey of Quantization Methods for Efficient Neural Network Inference
Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M. W., & Keutzer, K. (2022) · Low-Power Computer Vision · doi:10.1201/9781003162810-13 · Cited by 1,219
“As such, there is a large body of work that has proposed different solutions to address this [18, 25, 47, 52, 77, 82, 91, 92, 118, 120, 122, 127, 129, 133, 139, 147, 152, 157, 190, 192, 210, 241, 243, 252, 254, 279, 281].”
Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Tang, H., Liu, Z., Zhao, S., Lin, Y., Lin, J., Wang, H., & Han, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58604-1_41 · Cited by 733
Self-citationSpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
Wang, H., Zhang, Z., & Han, S. (2021) · 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00018 · Cited by 427
Self-citationStructured Pruning for Deep Convolutional Neural Networks: A Survey
He, Y., & Xiao, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3334614 · Cited by 363
Metadata
- Authors
- Wang, T., Wang, K., Cai, H., Lin, J., Liu, Z., Wang, H., Lin, Y., & Han, S.
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 2075-2084
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3035332806
- Cited by
- 187
- References
- 13
- FWCI
- 9.98
- Type
- conference paper
- Language
- en
- Open access
- green
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.