FedCoin: A Peer-to-Peer Payment System for Federated Learning
This addresses the incentive problem for data owners in federated learning, though it is incremental as it builds on existing blockchain and Shapley Value methods.
The paper tackles the computational cost and time of calculating Shapley Values for incentivizing data owners in federated learning by proposing FedCoin, a blockchain-based payment system that uses a proof-of-Shapley protocol to compute these values efficiently, with experimental results showing it can accurately compute SVs with bounded resources.
Federated learning (FL) is an emerging collaborative machine learning method to train models on distributed datasets with privacy concerns. To properly incentivize data owners to contribute their efforts, Shapley Value (SV) is often adopted to fairly assess their contribution. However, the calculation of SV is time-consuming and computationally costly. In this paper, we propose FedCoin, a blockchain-based peer-to-peer payment system for FL to enable a feasible SV based profit distribution. In FedCoin, blockchain consensus entities calculate SVs and a new block is created based on the proof of Shapley (PoSap) protocol. It is in contrast to the popular BitCoin network where consensus entities "mine" new blocks by solving meaningless puzzles. Based on the computed SVs, a scheme for dividing the incentive payoffs among FL clients with nonrepudiation and tamper-resistance properties is proposed. Experimental results based on real-world data show that FedCoin can promote high-quality data from FL clients through accurately computing SVs with an upper bound on the computational resources required for reaching consensus. It opens opportunities for non-data owners to play a role in FL.