Proof of Federated Learning: A Novel Energy-Recycling Consensus Algorithm

• Published in: IEEE transactions on parallel and distributed systems Vol. 32; no. 8; pp. 2074 - 2085
• Main Authors: Qu, Xidi, Wang, Shengling, Hu, Qin, Cheng, Xiuzhen
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Blockchain; Blockchains; Collaboration; Computational modeling; consensus algorithm; Cryptography; Data models; Federated learning; Game theory; incentive mechanism; Leakage; Machine learning; Miners; Model accuracy; Privacy; Recycling; Task analysis; Training; Training data; Verification

Proof of work (PoW), the most popular consensus mechanism for blockchain, requires ridiculously large amounts of energy but without any useful outcome beyond determining accounting rights among miners. To tackle the drawback of PoW, we propose a novel energy-recycling consensus algorithm, namely pro...