Blockchain-enabled federated learning with mechanism design

• Main Authors: Toyoda, Kentaroh, Zhao, Jun, Zhang, Allan Neng Sheng, Mathiopoulos, Panagiotis Takis
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Federated Learning; Decentralized Deep Learning
• Online Access: https://hdl.handle.net/10356/145988
• Institution: Nanyang Technological University

Federated learning (FL) is a promising decentralized deep learning technique that allows users to collaboratively update models without sharing their own data. However, due to its decentralized nature, no one can monitor workers’ behavior, and they may thus deviate protocols (e.g., participating wit...