Journal article · 2026 · Open access
Fast AI Model Partition for Split Learning Over Edge Networks
IEEE Transactions on Mobile Computing, 25(11), 19046–19061 · Published 1 July 2026 · DOI 10.1109/tmc.2026.3709072
In brief
“Fast AI Model Partition for Split Learning Over Edge Networks” is a 2026 journal article by Zuguang Li and 3 co-authors, published in IEEE Transactions on Mobile Computing. OpenAlex counts 4 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 4
- Most cited in
- 2026 (3)
- Field-weighted impact
- 4.55
- References
- 36
- Authors
- 4
Abstract
Split learning (SL) is a distributed learning paradigm that can enable computation-intensive artificial intelligence (AI) applications by partitioning AI models between mobile devices and edge servers. %fully utilizing distributed computing resources for computation-intensive mobile intelligence applications. However, the model partitioning problem in SL becomes challenging due to the diverse and complex architectures of AI models. In this paper, we formulate an optimal model partitioning problem to minimize training delay in SL. To solve the problem, we represent an arbitrary AI model as a directed acyclic graph (DAG), where the model's layers and inter-layer connections are mapped to vertices and edges, and training delays are captured as edge weights. Then, we propose a general model partitioning algorithm by transforming the problem into a minimum \textit{s-t} cut problem on the DAG. Theoretical analysis shows that the two problems are equivalent, such that the optimal model partition can be obtained via a maximum-flow method. Furthermore, taking AI models with block structures into consideration, we design a low-complexity block-wise model partitioning algorithm to determine the optimal model partition. Specifically, the algorithm simplifies the DAG by abstracting each block (i.e., a repeating component comprising multiple layers in an AI model) into a single vertex. Extensive experimental results on a hardware testbed equipped with NVIDIA Jetson devices demonstrate that the proposed solution can reduce algorithm running time by up to 13.0$\times$ and training delay by up to 38.95\%, compared to state-of-the-art baselines.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Li, Z., Wu, W., Wu, S., & Shen, X. (2026). Fast AI Model Partition for Split Learning Over Edge Networks. IEEE Transactions on Mobile Computing, 25(11), 19046–19061. https://doi.org/10.1109/tmc.2026.3709072
MLA 9
Li, Zuguang, et al. “Fast AI Model Partition for Split Learning Over Edge Networks.” IEEE Transactions on Mobile Computing, vol. 25, no. 11, 2026, pp. 19046–19061. https://doi.org/10.1109/tmc.2026.3709072.
Chicago
Li, Zuguang, Wen Wu, Shaohua Wu, and Xuemin Shen. 2026. “Fast AI Model Partition for Split Learning Over Edge Networks.” IEEE Transactions on Mobile Computing 25 (11): 19046–19061. https://doi.org/10.1109/tmc.2026.3709072.
Harvard
Li, Z. et al. (2026) ‘Fast AI Model Partition for Split Learning Over Edge Networks’, IEEE Transactions on Mobile Computing, 25(11), pp. 19046–19061. doi:10.1109/tmc.2026.3709072.
IEEE
Z. Li, W. Wu, S. Wu, and X. Shen, “Fast AI Model Partition for Split Learning Over Edge Networks,” IEEE Transactions on Mobile Computing, vol. 25, no. 11, pp. 19046–19061, 2026, doi: 10.1109/tmc.2026.3709072.
BibTeX
@article{li2026fast,
title = {{Fast AI Model Partition for Split Learning Over Edge Networks}},
author = {Li, Zuguang and Wu, Wen and Wu, Shaohua and Shen, Xuemin},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {11},
pages = {19046--19061},
doi = {10.1109/tmc.2026.3709072},
url = {https://doi.org/10.1109/tmc.2026.3709072}
}
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
- split learning
- model partitioning
- edge computing
- directed acyclic graphs
- s-t cut
- maximum flow
- distributed learning
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?
Li, Z., Wu, W., Wu, S., & Shen, X. (2026). Fast AI Model Partition for Split Learning Over Edge Networks. IEEE Transactions on Mobile Computing, 25(11), 19046–19061. https://doi.org/10.1109/tmc.2026.3709072
How many times has this paper been cited?
4 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 arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Zuguang Li, Wen Wu, Shaohua Wu, Xuemin Shen.
What is the DOI of this paper?
10.1109/tmc.2026.3709072, permanently at https://doi.org/10.1109/tmc.2026.3709072. 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.