Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource
On the map: Efficient LLM inference and serving → Early exit and edge inference
Abstract (arXiv)
Deep Neural Networks (DNNs) have significantly improved the accuracy of intelligent applications on mobile devices. DNN surgery, which partitions DNN processing between mobile devices and multi-access edge computing (MEC) servers, can enable real-time inference despite the computational limitations of mobile devices. However, DNN surgery faces a critical challenge: determining the optimal computing resource demand from the server and the corresponding partition strategy, while considering both inference latency and MEC server usage costs. This problem is compounded by two factors: (1) the finite computing capacity of the MEC server, which is shared among multiple devices, leading to inter-dependent demands, and (2) the shift in modern DNN architecture from chains to directed acyclic graphs (DAGs), which complicates potential solutions. In this paper, we introduce a novel Decentralized DNN Surgery (DDS) framework. We formulate the partition strategy as a min-cut and propose a resource allocation game to adaptively schedule the demands of mobile devices in an MEC environment. We prove the existence of a Nash Equilibrium (NE), and develop an iterative algorithm to efficiently reach the NE for each device. Our extensive experiments demonstrate that DDS can effectively handle varying MEC scenarios, achieving up to 1.25× acceleration compared to the state-of-the-art algorithm.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving. Builds on 14 of its 46 references that are in the map. First posted on arXiv 21 Jun 2023.
Builds on
14 of 46 references.
References · 14
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
- 2019Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computingcited by 228
- 2019Self-Driving Cars: A Surveycited by 148
- 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 134
- 2018The Mechanics of n-Player Differentiable Gamescited by 118
- 2020CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devicescited by 67
- 2018Reinforcement Learning for UAV Attitude Controlcited by 48
Built on by
Citing papers per year: 2024: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon
- 2026Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds
- 2023AdaMEC: Towards a Context-Adaptive and Dynamically-Combinable DNN Deployment Framework for Mobile Edge Computing
- 2025Dynamic Pricing for On-Demand DNN Inference in the Edge-AI Market
- 2024Distributed Inference on Mobile Edge and Cloud: An Early Exit based Clustering Approach
- 2024Distributed Convolutional Neural Network Training on Mobile and Edge Clusters
- 2025DistrEE: Distributed Early Exit of Deep Neural Network Inference on Edge Devices
- 2022Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing