User: Guest  Login
Title:

Variant Parallelism: Lightweight Deep Convolutional Models for Distributed Inference on IoT Devices

Document type:
Zeitschriftenaufsatz
Author(s):
Asadi, Navidreza; Goudarzi, Maziar
Abstract:
Two major techniques are commonly used to meet real-time inference limitations when distributing models across resource-constrained IoT devices: 1) model parallelism (MP) and 2) class parallelism (CP). In MP, transmitting bulky intermediate data (orders of magnitude larger than input) between devices imposes huge communication overhead. Although CP solves this problem, it has limitations on the number of submodels. In addition, both solutions are fault intolerant, an issue when deployed on edge...     »
Journal title:
IEEE Internet of Things Journal
Year:
2024
Journal volume:
11
Journal issue:
1
Pages contribution:
345-352
Fulltext / DOI:
doi:10.1109/jiot.2023.3285877
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
E-ISSN:
2327-46622372-2541
Date of publication:
01.01.2024
Semester:
WS 23-24
 BibTeX