Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource
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$\times$ acceleration compared to the state-of-the-art algorithm.
Code (0)
등록된 구현이 없습니다.
Tasks
Edge-computingSimilar Papers 제목 키워드 기반
Selfish Sparse RNN Training
Sparse neural networks have been widely applied to reduce the computational demands of training and deploying over-parameterized deep neural networks. For inference acceleration, methods that discover a sparse network fr…
Dynamic Tolling for Inducing Socially Optimal Traffic Loads
How to design tolls that induce socially optimal traffic loads with dynamically arriving travelers who make selfish routing decisions? We propose a two-timescale discrete-time stochastic dynamics that adaptively adjusts …
Minimally Invasive Surgery for Sparse Neural Networks in Contrastive Manner
With the development of deep learning, neural networks tend to be deeper and larger to achieve good performance. Trained models are more compute-intensive and memory-intensive, which lead to the big challenges on mem…
Knowledge DistillationModel CompressionNeural Network CompressionUnraveling the Connection: How Cognitive Workload Shapes Intent Recognition in Robot-Assisted Surgery
Robot-assisted surgery has revolutionized the healthcare industry by providing surgeons with greater precision, reducing invasiveness, and improving patient outcomes. However, the success of these surgeries depends heavi…
Intent RecognitionRethinking Efficient Graph Coarsening via a Non-Selfishness Principle
Graph coarsening is a graph dimensionality reduction technique that aims to construct a smaller and more tractable graph while preserving the essential structural and semantic properties of the original graph. However, m…
Dimensionality Reduction