Long-Term Proof-of-Contribution: An Incentivized Consensus Algorithm for Blockchain-Enabled Federated Learning

The surge in data collected by local devices has given rise to a distributed machine learning architecture named F ederated L earning (FL) for privacy-preserving model training. However, the security of centralized aggregation of local models becomes a primary concern, which can be mitigated by B lockchain-enabled F ederated L earning (BFL) to facilitate decentralized model aggregation. In BFL, consensus and incentive are two of the key components that impact the scalability, security, and consistency of the system. Existing joint solutions focus on selecting a block producer based on client contributions to model training but overlook contributions to blockchain consensus and lack consideration for correlations across communication rounds, inevitably affecting incentive performance. Motivated by these, we make the first attempt to achieve blockchain consensus with a long-term incentive guarantee for BFL systems. Following a generalizable BFL workflow, we decouple the global contribution of BFL clients into four rigorously modeled metrics, and formulate the block producer selection problem as a long-term total contribution maximization problem with reward constraints. A L ong-term P roof- o f- C ontribution algorithm named LPoC is developed to handle this problem efficiently. In each communication round, LPoC identifies an optimal block producer that can maximize total contributions from a long-term perspective while allocating rewards to continuously motivate clients to contribute to BFL. We provide a detailed analysis of time complexity and performance bounds, followed by extensive experimental evaluations. The results demonstrate the effectiveness of LPoC in maximizing long-term total contribution, improving consensus efficiency, and upgrading training performance.