ScissionLite: accelerating distributed deep learning with lightweight data compression for IIoT

Hyunho Ahn, Munkyu Lee, Sihoon Seong, Gap-Joo Na, In-Geol Chun, Blesson Varghese, Cheol-Ho Hong

Research output: Contribution to journalArticlepeer-review


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.
Original languageEnglish
Number of pages11
JournalIEEE Transactions on Industrial Informatics
VolumeEarly Access
Early online date24 Jun 2024
Publication statusE-pub ahead of print - 24 Jun 2024


  • Edge computing
  • IIoT
  • Deep neural networks
  • Model slicing
  • Inference


Dive into the research topics of 'ScissionLite: accelerating distributed deep learning with lightweight data compression for IIoT'. Together they form a unique fingerprint.

Cite this