BROWSE
Detail
Journal Article
ScissionLite: Accelerating Distributed Deep Learning With Lightweight Data Compression for IIoT
Cited 1 time in 
Share 
Share
- Authors
- Hyunho Ahn, Munkyu Lee, Sihoon Seong, Gap-Joo Na, In-Geol Chun, Blesson Varghese, Cheol-Ho Hong
- Issue Date
- 2024-10
- Citation
- IEEE Transactions on Industrial Informatics, v.20, no.10, pp.11950-11960
- ISSN
- 1551-3203
- Publisher
- Institute of Electrical and Electronics Engineers
- Language
- English
- Type
- Journal Article
- Abstract
- Industrial Internet of Things (IIoT) applications can greatly benefit from leveraging edge computing. For instance, applications relying on deep neural network (DNN) models can be sliced and distributed across IIoT devices and the network edge to reduce inference latency. However, low network performance between IIoT devices and the edge often becomes a bottleneck. In this study, we propose ScissionLite, a holistic framework designed to accelerate distributed DNN inference using lightweight data compression. Our compression method features a novel lightweight down/upsampling network tailored for performance-limited IIoT devices, which is inserted at the slicing point of a DNN model to reduce outbound network traffic without causing a significant drop in accuracy. In addition, we have developed a benchmarking tool to accurately identify the optimal slicing point of the DNN for the best inference latency. ScissionLite improves inference latency by up to 15.7× with minimal accuracy degradation.
- KSP Keywords
- Benchmarking Tools, Compression method, Deep neural network(DNN), Edge Computing, Industrial internet of things, Network performance, data compression, deep learning(DL), internet of things(IoT), network traffic, neural network(NN)