Enhancing Scalability and Reliability in Semi-Decentralized Federated Learning With Blockchain: Trust Penalization and Asynchronous Functionality
This work addresses scalability and reliability problems for collaborative machine learning systems, but it appears incremental as it builds on existing semi-decentralized federated learning with blockchain integration.
The paper tackled scalability and reliability issues in distributed federated learning by integrating blockchain with a trust penalization mechanism and asynchronous functionality, resulting in a system that enhances trustworthiness and efficiency in model updates.
The paper presents an innovative approach to address the challenges of scalability and reliability in Distributed Federated Learning by leveraging the integration of blockchain technology. The paper focuses on enhancing the trustworthiness of participating nodes through a trust penalization mechanism while also enabling asynchronous functionality for efficient and robust model updates. By combining Semi-Decentralized Federated Learning with Blockchain (SDFL-B), the proposed system aims to create a fair, secure and transparent environment for collaborative machine learning without compromising data privacy. The research presents a comprehensive system architecture, methodologies, experimental results, and discussions that demonstrate the advantages of this novel approach in fostering scalable and reliable SDFL-B systems.