Task-Aware Collaborative Inference and Fine-Grained DNN Partitioning in MEC Networks
IEEE Transactions on Mobile Computing · 2026-06 · 25 (6) · 8911-8927
DOI: 10.1109/tmc.2025.3650680 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-06. Verfasst von Guanlei Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation of China, Fundamental Research Funds for the Beijing University of Posts and Telecommunications.
Abstract (Originalsprache)
Mobile devices (MDs) are increasingly incorporating deep neural network (DNN) inference into their systems due to the rapid growth of intelligent applications. Mobile edge computing-based distributed DNN collaborative inference has gained popularity due to limited on-device computation and energy budgets. However, the resource competition among MDs, along with the coupling of collaborative inference tasks across MDs and servers, creates significant challenges for efficient resource management. This issue is further exacerbated by the complexity of directed acyclic graph (DAG)-structured DNNs. Most prior studies do not jointly address the dual challenges of partitioning complex-structured DNNs and leveraging advanced optimization for collaborative inference, and their resilience to channel condition fluctuations remains underexplored. To address these challenges, we propose a novel task-aware collaborative inference framework. First, we devise a fine-grained partitioning point search algorithm based on a bidirectional graph linked list, which enables one-dimensional and flexible partitioning of DAG-structured DNNs. We then reformulate the problem of minimizing collaborative inference energy consumption and latency as a task-aware Markov decision process (MDP), which partitions each user’s inference task queue into consecutive task windows for resource allocation. Building on this, we propose an Embedded Multi-Agent Hybrid Proximal Policy Optimization (EMH-PPO) algorithm to learn effective policies. Extensive experiments conducted across diverse network scenarios reveal that, compared to local DNN inference on MDs, our proposed method reduces inference latency by up to 64% and energy consumption by up to 46%.
Förderung
- National Natural Science Foundation of China
- Beijing Natural Science Foundation of China
- Fundamental Research Funds for the Beijing University of Posts and Telecommunications
Zitieren
APA
Zhang, G., Zhang, Q., Feng, L., Zhou, F., Donta, P. K., & Dustdar, S. (2026). Task-Aware Collaborative Inference and Fine-Grained DNN Partitioning in MEC Networks. IEEE Transactions on Mobile Computing, 25(6), 8911-8927. https://doi.org/10.1109/tmc.2025.3650680
Vancouver
Zhang G, Zhang Q, Feng L, Zhou F, Donta PK, Dustdar S. Task-Aware Collaborative Inference and Fine-Grained DNN Partitioning in MEC Networks. IEEE Transactions on Mobile Computing. 2026;25(6):8911-8927. doi:10.1109/tmc.2025.3650680
BibTeX
@article{Zhang2026,
author = {Zhang, Guanlei and Zhang, Qiyang and Feng, Lei and Zhou, Fanqin and Donta, Praveen Kumar and Dustdar, Schahram},
title = {Task-Aware Collaborative Inference and Fine-Grained DNN Partitioning in MEC Networks},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {6},
pages = {8911--8927},
doi = {10.1109/tmc.2025.3650680}
}
EUVIMED