Journal article · 2023 · Open access
Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference
ACM Transactions on Architecture and Code Optimization, 20(4), 1–24 · Published 30 August 2023 · DOI 10.1145/3617688
In brief
“Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference” is a 2023 journal article by Donglei Wu and 7 co-authors, published in ACM Transactions on Architecture and Code Optimization. OpenAlex counts 14 citations as of 19 November 2026, which puts it in the top 7% of works published in 2023 by citations. It is open access under a CC BY-NC-SA licence: the full text is free to read at ACM Transactions on Architecture and Code Optimization.
- Citations
- 14
- Most cited in
- 2025 (7)
- Field-weighted impact
- 0.96
- References
- 52
- Authors
- 8
Abstract
Deep Neural Networks (DNNs) have achieved remarkable success in various real-world applications. However, running a Deep Neural Network (DNN) typically requires hundreds of megabytes of memory footprints, making it challenging to deploy on resource-constrained platforms such as mobile devices and IoT. Although mainstream DNNs compression techniques such as pruning, distillation, and quantization can reduce the memory overhead of model parameters during DNN inference, they suffer from three limitations: (i) low model compression ratio for the lightweight DNN structures with little redundancy, (ii) potential degradation in model inference accuracy, and (iii) inadequate memory compression ratio is attributable to ignoring the layering property of DNN inference. To address these issues, we propose a lightweight memory-efficient DNN inference framework called Smart-DNN+, which significantly reduces the memory costs of DNN inference without degrading the model quality. Specifically, ① Smart-DNN+ applies a layerwise binary-quantizer with a remapping mechanism to greatly reduce the model size by quantizing the typical floating-point DNN weights of 32-bit to the 1-bit signs layer by layer. To maintain model quality, ② Smart-DNN+ employs a bucket-encoder to keep the compressed quantization error by encoding the multiple similar floating-point residuals into the same integer bucket IDs. When running the compressed DNN in the user’s device, ③ Smart-DNN+ utilizes a partially decompressing strategy to greatly reduce the required memory overhead by first loading the compressed DNNs in memory and then dynamically decompressing the required materials for model inference layer by layer. Experimental results on popular DNNs and datasets demonstrate that Smart-DNN+ achieves lower 0.17%–0.92% memory costs at lower runtime overheads compared with the states of the art without degrading the inference accuracy. Moreover, Smart-DNN+ potentially reduces the inference runtime up to 2.04× that of conventional DNN inference workflow.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wu, D., Yang, W., Zou, X., Xia, W., Li, S., Hu, Z., Zhang, W., & Fang, B. (2023). Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference. ACM Transactions on Architecture and Code Optimization, 20(4), 1–24. https://doi.org/10.1145/3617688
MLA 9
Wu, Donglei, et al. “Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference.” ACM Transactions on Architecture and Code Optimization, vol. 20, no. 4, 2023, pp. 1–24. https://doi.org/10.1145/3617688.
Chicago
Wu, Donglei, Weihao Yang, Xiangyu Zou, Wen Xia, Shiyi Li, Zhenbo Hu, Weizhe Zhang, and Binxing Fang. 2023. “Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference.” ACM Transactions on Architecture and Code Optimization 20 (4): 1–24. https://doi.org/10.1145/3617688.
Harvard
Wu, D. et al. (2023) ‘Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference’, ACM Transactions on Architecture and Code Optimization, 20(4), pp. 1–24. doi:10.1145/3617688.
IEEE
D. Wu et al., “Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference,” ACM Transactions on Architecture and Code Optimization, vol. 20, no. 4, pp. 1–24, 2023, doi: 10.1145/3617688.
BibTeX
@article{wu2023smart,
title = {{Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference}},
author = {Wu, Donglei and Yang, Weihao and Zou, Xiangyu and Xia, Wen and Li, Shiyi and Hu, Zhenbo and Zhang, Weizhe and Fang, Binxing},
journal = {ACM Transactions on Architecture and Code Optimization},
year = {2023},
volume = {20},
number = {4},
pages = {1--24},
doi = {10.1145/3617688},
url = {https://doi.org/10.1145/3617688}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 3 | |
| 2025 | 7 | |
| 2026 | 4 |
Its field-weighted citation impact is 0.96: it has been cited 0.96 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- neural network compression
- memory-efficient inference
- binary quantization
- quantization error
- partial decompression
- resource-constrained devices
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Wu, D., Yang, W., Zou, X., Xia, W., Li, S., Hu, Z., Zhang, W., & Fang, B. (2023). Smart-DNN+: A Memory-efficient Neural Networks Compression Framework for the Model Inference. ACM Transactions on Architecture and Code Optimization, 20(4), 1–24. https://doi.org/10.1145/3617688
How many times has this paper been cited?
14 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at ACM Transactions on Architecture and Code Optimization: sign in and open the PDF from this page.
Who wrote this paper?
Donglei Wu, Weihao Yang, Xiangyu Zou, Wen Xia, Shiyi Li, Zhenbo Hu, Weizhe Zhang, Binxing Fang.
What is the DOI of this paper?
10.1145/3617688, permanently at https://doi.org/10.1145/3617688. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.