Skip to main navigation Skip to search Skip to main content

DeepSwarm: towards swarm deep learning with bi-directional optimization of data acquisition and processing

  • Sicong LIU
  • , Bin GUO*
  • , Ziqi WANG
  • , Lehao WANG
  • , Zimu ZHOU
  • , Xiaochen LI
  • , Zhiwen YU
  • *Corresponding author for this work

Research output: Journal Publications and ReviewsLetter

Abstract

Inspired by the collective intelligence observed in natural swarms, where individual proactive actions contribute to superior global performance, we advocate for a shift towards Swarm DL. By harnessing the potential of physically adjacent mobile devices in IoT scenarios, we present DeepSwarm, a closed-loop system framework architecture. DeepSwarm facilitates bidirectional optimization between data acquisition and processing, aiming to push the performance boundaries of on-device DL Specifically, DeepSwarm addresses the requirements of proactive Swarm DL by decomposing them into layers: self-organized swarm data acquisition and self-adaptive, self-evolutionary swarm data processing. © Higher Education Press 2025.
Original languageEnglish
Article number193501
JournalFrontiers of Computer Science
Volume19
Issue number3
Online published20 Nov 2024
DOIs
Publication statusPublished - Mar 2025

Funding

The work was supported by the National Science Fund for Distinguished Young Scholars (62025205), the National Natural Science Foundation of China (Grant Nos. 62032020, 62102317), CityU APRC Grant (9610633).

Fingerprint

Dive into the research topics of 'DeepSwarm: towards swarm deep learning with bi-directional optimization of data acquisition and processing'. Together they form a unique fingerprint.

Cite this