Journal article · 2023 · Open access

Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration

Huamei Qi, Fang Ren, Leilei Wang, Ping Jiang, Shaohua Wan, Xiaoheng Deng

ACM Transactions on Embedded Computing Systems, 23(1), 1–25 · Published 28 November 2023 · DOI 10.1145/3634704

Open PDFView at the publisherCite this paper

In brief

“Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration” is a 2023 journal article by Huamei Qi and 5 co-authors, published in ACM Transactions on Embedded Computing Systems. OpenAlex counts 38 citations as of 19 November 2026. It is open access: the full text is free to read at ACM Transactions on Embedded Computing Systems.

Citations
38
Most cited in
2025 (20)
Field-weighted impact
2.95
References
44
Authors
6

Abstract

Edge intelligence has emerged as a promising paradigm to accelerate DNN inference by model partitioning, which is particularly useful for intelligent scenarios that demand high accuracy and low latency. However, the dynamic nature of the edge environment and the diversity of end devices pose a significant challenge for DNN model partitioning strategies. Meanwhile, limited resources of the edge server make it difficult to manage resource allocation efficiently among multiple devices. In addition, most of the existing studies disregard the different service requirements of the DNN inference tasks, such as its high accuracy-sensitive or high latency-sensitive. To address these challenges, we propose a Multi-Compression Scale DNN Inference Acceleration (MCIA) based on cloud-edge-end collaboration. We model this problem as a mixed-integer multi-dimensional optimization problem, jointly optimizing the DNN model version choice, the partitioning choice, and the allocation of computational and bandwidth resources to maximize the tradeoff between inference accuracy and latency depending on the property of the tasks. Initially, we train multiple versions of DNN inference models with different compression scales in the cloud, and deploy them to end devices and edge server. Next, a deep reinforcement learning-based algorithm is developed for joint decision making of adaptive collaborative inference and resource allocation based on the current multi-compression scale models and the task property. Experimental results show that MCIA can adapt to heterogeneous devices and dynamic networks, and has superior performance compared with other methods.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Qi, H., Ren, F., Wang, L., Jiang, P., Wan, S., & Deng, X. (2023). Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration. ACM Transactions on Embedded Computing Systems, 23(1), 1–25. https://doi.org/10.1145/3634704

MLA 9

Qi, Huamei, et al. “Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration.” ACM Transactions on Embedded Computing Systems, vol. 23, no. 1, 2023, pp. 1–25. https://doi.org/10.1145/3634704.

Chicago

Qi, Huamei, Fang Ren, Leilei Wang, Ping Jiang, Shaohua Wan, and Xiaoheng Deng. 2023. “Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration.” ACM Transactions on Embedded Computing Systems 23 (1): 1–25. https://doi.org/10.1145/3634704.

Harvard

Qi, H. et al. (2023) ‘Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration’, ACM Transactions on Embedded Computing Systems, 23(1), pp. 1–25. doi:10.1145/3634704.

IEEE

H. Qi, F. Ren, L. Wang, P. Jiang, S. Wan, and X. Deng, “Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration,” ACM Transactions on Embedded Computing Systems, vol. 23, no. 1, pp. 1–25, 2023, doi: 10.1145/3634704.

BibTeX

@article{qi2023multi,
  title     = {{Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration}},
  author    = {Qi, Huamei and Ren, Fang and Wang, Leilei and Jiang, Ping and Wan, Shaohua and Deng, Xiaoheng},
  journal   = {ACM Transactions on Embedded Computing Systems},
  year      = {2023},
  volume    = {23},
  number    = {1},
  pages     = {1--25},
  doi       = {10.1145/3634704},
  url       = {https://doi.org/10.1145/3634704}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202311
202499
20252020
202688

Its field-weighted citation impact is 2.95: it has been cited 2.95 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 Networks and Communications › IoT and Edge/Fog Computing

  • DNN inference acceleration
  • model partitioning
  • cloud-edge-end collaboration
  • edge AI
  • model compression
  • resource allocation
  • bandwidth allocation
  • mixed integer programming

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Qi, H., Ren, F., Wang, L., Jiang, P., Wan, S., & Deng, X. (2023). Multi-Compression Scale DNN Inference Acceleration based on Cloud-Edge-End Collaboration. ACM Transactions on Embedded Computing Systems, 23(1), 1–25. https://doi.org/10.1145/3634704

How many times has this paper been cited?

38 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 Embedded Computing Systems: sign in and open the PDF from this page.

Who wrote this paper?

Huamei Qi, Fang Ren, Leilei Wang, Ping Jiang, Shaohua Wan, Xiaoheng Deng.

What is the DOI of this paper?

10.1145/3634704, permanently at https://doi.org/10.1145/3634704. 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.