.png){kind=icon}
返回
Mixed-Precision Neural Architecture Search and Dynamic Split Point Selection for Split Computing
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2024.3455251.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Split computing (SC) is an emerging technique to perform the inference task of deep neural network (DNN) models using both mobile devices and cloud/edge servers in a hybrid manner. To improve the end-to-end inference time over the network, SC splits a single DNN model into a head model and a tail model for deployment on the mobile device and the server, respectively. A further extension of SC, referred to as dynamic SC (DSC), determines the split point dynamically depending on various network conditions such as bandwidth. This article proposes a DNN optimization approach for DSC based on mixed-precision quantization. Given a vanilla DNN model, our work optimizes the given model in two steps. First, a DSC-aware mixed-precision layer-wise quantization is performed statically via neural architecture search to generate multiple potential split points. Then a bitwidth-wise DSC algorithm is applied to dynamically select one optimal split point among the candidate points. Our evaluation on the EfficientNet-B0 and EfficientNet-B3 architectures demonstrated that our work provides more effective split points than existing quantization works while mitigating the degradation of inference accuracy. In terms of the end-to-end inference time, on the EfficientNet-B0 (B3) architecture, our work obtained relative average and maximum gains of 9.12% (4.05%) and 27.49% (12.42%), respectively, over a state-of-the-art mix-precision quantization work while achieving comparable accuracy.
Keyword:
Quantization (signal)
Computational modeling
Servers
Optimization
Heuristic algorithms
Accuracy
Delays
Artificial neural networks
Deep neural networks
split computing
mixed-precision quantization
neural architecture search
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Kitsune: An Ensemble of Autoencoders for Online Network Intrusion DetectionKitsune: 用于在线网络入侵检测的自动编码器的集合OAAI
OAAI分享收藏Numerical Analysis of Thermal Stress for a Stack of Planar Solid Oxide Fuel Cells平板固体氧化物燃料电池堆热应力的数值分析.png)
EnergiesOAAI
EnergiesIF0
OAAI分享收藏Two-dimensional gel proteome analysis of honeybee, Apis mellifera, worker red-eye pupa hemolymphApidologieOAAI
ApidologieIF0
OAAI分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges深度学习应用的拆分计算和早期退出: 调查和研究挑战OAAI
OAAI分享收藏
查看更多内容