Loading web-font TeX/Main/Regular
Privacy-Preserving Collaborative Learning With Linear Communication Complexity | IEEE Journals & Magazine | IEEE Xplore

Privacy-Preserving Collaborative Learning With Linear Communication Complexity


Abstract:

Collaborative machine learning enables privacy-preserving training of machine learning models without collecting sensitive client data. Despite recent breakthroughs, comm...Show More

Abstract:

Collaborative machine learning enables privacy-preserving training of machine learning models without collecting sensitive client data. Despite recent breakthroughs, communication bottleneck is still a major challenge against its scalability to larger networks. To address this challenge, in this work we propose PICO, the first collaborative learning framework with linear communication complexity, significantly improving over the quadratic state-of-the-art, under formal information-theoretic privacy guarantees. Theoretical analysis demonstrates that PICO slashes the communication cost while achieving equal computational complexity, adversary resilience, robustness to client dropouts, and model accuracy to the state-of-the-art. Extensive experiments demonstrate up to 91\times reduction in the communication overhead, and up to 8\times speed-up in the wall-clock training time compared to the state-of-the-art. As such, PICO addresses a key technical challenge in multi-party collaborative learning, paving the way for future large-scale privacy-preserving learning frameworks.
Published in: IEEE Transactions on Information Theory ( Volume: 70, Issue: 8, August 2024)
Page(s): 5857 - 5887
Date of Publication: 19 December 2023

ISSN Information:

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.