SONAR Web: A Platform-Agnostic Framework for Real-Time Decentralized Learning Across Heterogeneous Edge Clients
Name
3737899.3768523.pdf
Size
780.35 KB
Format
Adobe PDF
Checksum (MD5)
f6fb96c392cda2635a573309108ed9b8
Author(s)
Yuan, Joyce
Le, Brian
Le, Kathryn
Shi, Yichuan
Singh, Abhishek
Sharma, Rishi
Patricio, Angel
Raskar, Ramesh
Date Issued
December 2, 2025
Publisher
ACM|Federated Learning and Edge AI for Privacy and Mobility
Citation
Joyce Yuan, Brian Le, Kathryn Le, Yichuan Shi, Abhishek Singh, Rishi Sharma, Angel Patricio, and Ramesh Raskar. 2025. SONAR Web: A Platform-Agnostic Framework for Real-Time Decentralized Learning Across Heterogeneous Edge Clients. In Proceedings of the Federated Learning and Edge AI for Privacy and Mobility (FLEdge-AI '25). Association for Computing Machinery, New York, NY, USA, 52–58.
Version
Final published version
Abstract
Most federated learning (FL) frameworks assume reliable networks and homogeneous devices, limiting their applicability in mobile and edge environments where connectivity is intermittent and devices are highly heterogeneous. We introduce SONAR Web, an open-source framework for fully decentralized, cross-platform collaborative learning between browsers, servers, tablets, and smartphones. SONAR Web decouples the learning protocol from the underlying client platform through a platform-agnostic configuration interface—enabling Python, JavaScript, and mobile clients to seamlessly interoperate in real time. By combining peer-to-peer RTC protocols with communication-efficient techniques from FL, SONAR Web supports privacy-preserving training without centralized orchestration. We demonstrate SONAR Web's robustness through deployments on real-world devices and networks, showing resilience under heterogeneous network conditions and resource variability. SONAR Web provides a unified, language-agnostic interface for decentralized learning, enabling seamless collaboration across heterogeneous devices and runtimes—advancing scalable, inclusive, and real-time model training at the mobile and edge frontier.
Description
FLEdge-AI ’25, November 4-8, 2025, Hong Kong, China
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Program in Media Arts and Sciences (Massachusetts Institute of Technology)
Terms of Use
Creative Commons Attribution-ShareAlike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3737899.3768523
