Privacy-Aware Joint DNN Model Deployment and Partitioning Optimization for Collaborative Edge Inference Services
- 8 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (5) , 3079-3092
Abstract
Edge inference (EI) has emerged as a promising paradigm to address the growing limitations of cloud-based Deep Neural Network (DNN) inference services, such as high response latency, limited scalability, and severe data privacy exposure. However, deploying DNN models on resource-constrained edge devices introduces additional challenges, including limited computation/storage resources, dynamic service demands, and heightened privacy risks. To address these challenges, this paper presents a novel privacy-aware optimization framework that jointly tackles DNN model deployment, user-server association, and model partitioning, aiming to minimize long-term average inference delay under resource and privacy constraints. We formulate the problem as a complex, NP-hard stochastic optimization problem, emphasizing its inherent complexity. To efficiently handle system dynamics and computational complexity, we adopt a Lyapunov-based approach to transform the long-term objective into tractable per-slot decisions. Additionally, we introduce a coalition formation game model to facilitate adaptive user-server association, and design a greedy algorithm for model deployment within each coalition. Extensive simulations demonstrate that the proposed algorithm significantly reduces inference delay while consistently satisfying privacy constraints, outperforming baselines across diverse scenarios.Keywords
All Related Versions
Funding Information
- Natural Science Foundation of Jiangsu Province (BK20240780)
- National Natural Science Foundation of China (62271424)
- Shanghai Pujiang Programme (24PJD117)
- National Natural Science Foundation of China Basic Science Research Center Program (62088101)
- Shanghai Municipal Science and Technology Major Project (2021SHZDZX0100)
- Chinese Academy of Engineering, Strategic Research and Consulting Program (2023-XZ-65)
- Natural Science Foundation of Qingdao Municipality (25-1-1-106-zyyd-jch)
This publication has 46 references indexed in Scilit:
- Energy-optimal DNN model placement in UAV-enabled edge computing networksDigital Communications and Networks, 2024
- Privacy-Aware Adaptive Model Splitting for Device-Edge Co Inference2023
- Privacy‐preserving model splitting and quality‐aware device association for federated edge learningSoftware: Practice and Experience, 2023
- LMIE-BERT: A Learnable Method for Inter-Layer Ensembles to Accelerate Inference of BERT-Style Pre-trained Models2023
- A Survey on Collaborative DNN Inference for Edge IntelligenceMachine Intelligence Research, 2023
- Joint multi-user DNN partitioning and task offloading in mobile edge computingAd Hoc Networks, 2023
- Design possibilities and challenges of DNN models: a review on the perspective of end devicesArtificial Intelligence Review, 2022
- Privacy-Aware Edge Computing Based on Adaptive DNN Partitioning2019
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Scaling for edge inference of deep neural networksNature Electronics, 2018