Journal article · 2026

DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference

Guan Wang, Wenhao Fan, Xiao Li, Guangtao Zhou, Liang Xin, Zhaoyang Yu, Yuanan Liu

IEEE Transactions on Mobile Computing, 25(8), 12704–12721 · Published 13 March 2026 · DOI 10.1109/tmc.2026.3673729

View at the publisherCite this paper

In brief

“DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference” is a 2026 journal article by Guan Wang and 6 co-authors, published in IEEE Transactions on Mobile Computing. OpenAlex counts 3 citations as of 19 November 2026, which puts it in the top 5% of works published in 2026 by citations. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
3
Most cited in
2026 (3)
Field-weighted impact
4.55
References
34
Authors
7

Abstract

By reducing the size of transmitted data between device-side and edge-side machine learning model parts, intermediate activation (IA) compression can alleviate communication overhead, lower latency, and conserve energy, thus enhancing the model partitioning in edge-device collaborative inference scenarios. However, existing studies lack refined resource allocation and fail to jointly optimize edge-device communication and computing resources… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

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

APA 7

Wang, G., Fan, W., Li, X., Zhou, G., Xin, L., Yu, Z., & Liu, Y. (2026). DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference. IEEE Transactions on Mobile Computing, 25(8), 12704–12721. https://doi.org/10.1109/tmc.2026.3673729

MLA 9

Wang, Guan, et al. “DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference.” IEEE Transactions on Mobile Computing, vol. 25, no. 8, 2026, pp. 12704–12721. https://doi.org/10.1109/tmc.2026.3673729.

Chicago

Wang, Guan, Wenhao Fan, Xiao Li, Guangtao Zhou, Liang Xin, Zhaoyang Yu, and Yuanan Liu. 2026. “DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference.” IEEE Transactions on Mobile Computing 25 (8): 12704–12721. https://doi.org/10.1109/tmc.2026.3673729.

Harvard

Wang, G. et al. (2026) ‘DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference’, IEEE Transactions on Mobile Computing, 25(8), pp. 12704–12721. doi:10.1109/tmc.2026.3673729.

IEEE

G. Wang et al., “DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference,” IEEE Transactions on Mobile Computing, vol. 25, no. 8, pp. 12704–12721, 2026, doi: 10.1109/tmc.2026.3673729.

BibTeX

@article{wang2026based,
  title     = {{DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference}},
  author    = {Wang, Guan and Fan, Wenhao and Li, Xiao and Zhou, Guangtao and Xin, Liang and Yu, Zhaoyang and Liu, Yuanan},
  journal   = {IEEE Transactions on Mobile Computing},
  year      = {2026},
  volume    = {25},
  number    = {8},
  pages     = {12704--12721},
  doi       = {10.1109/tmc.2026.3673729},
  url       = {https://doi.org/10.1109/tmc.2026.3673729}
}

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

Topic and keywords

Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing

  • model partitioning
  • resource allocation
  • transmit power allocation
  • deep reinforcement learning
  • communication cost reduction
  • inference latency
  • energy consumption

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?

Wang, G., Fan, W., Li, X., Zhou, G., Xin, L., Yu, Z., & Liu, Y. (2026). DRL-Based Adaptive Model Partitioning, Intermediate Activation Compression, and Resource Allocation for Edge-Device Collaborative Inference. IEEE Transactions on Mobile Computing, 25(8), 12704–12721. https://doi.org/10.1109/tmc.2026.3673729

How many times has this paper been cited?

3 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?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Guan Wang, Wenhao Fan, Xiao Li, Guangtao Zhou, Liang Xin, Zhaoyang Yu, Yuanan Liu.

What is the DOI of this paper?

10.1109/tmc.2026.3673729, permanently at https://doi.org/10.1109/tmc.2026.3673729. 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.