What is it about?
We design and evaluate a novel Blockchain-based Federated Learning (BFL) framework, and resolve the identified challenges in vanilla BFL with greater flexibility and incentive mechanism called FAIR-BFL. In contrast to existing works, FAIR-BFL offers unprecedented flexibility via the modular design, allowing adopters to adjust its capabilities following business demands in a dynamic fashion.
Featured Image
Photo by Choong Deng Xiang on Unsplash
Why is it important?
Vanilla Federated learning (FL) relies on the centralized global aggregation mechanism and assumes that all clients are honest. This makes it a challenge for FL to alleviate the single point of failure and dishonest clients. These impending challenges in the design philosophy of FL call for BFL due to the benefits of coupling FL and blockchain (e.g., democracy, incentive, and immutability). However, one problem in vanilla BFL is that its capabilities do not follow adopters’ needs in a dynamic fashion. Besides, vanilla BFL relies on unverifiable clients’ self-reported contributions like data size because checking clients’ raw data is not allowed in FL for privacy concerns. Solving the above challenges is imminent for BFL development.
Perspectives
This work addresses the privacy concerns and incentive challenges faced by vanilla BFL. Through the novel contribution recognition mechanism, personalized rewards can be issued to participants, which also gives BFL the ability to resist malicious attacks. The proposed FAIR-BFL framework is more robust and application-oriented.
Dr. Rongxin Xu
Hunan University
Read the Original
This page is a summary of: FAIR-BFL: Flexible and Incentive Redesign for Blockchain-based Federated Learning, August 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3545008.3545040.
You can read the full text:
Resources
Contributors
The following have contributed to this page
