Proof-of-Collaborative-Learning: A Multi-winner Federated Learning Consensus Algorithm

TL;DR

Proof-of-Collaborative-Learning (PoCL) reimagines blockchain consensus as a multi-winner federated learning task to reduce energy waste from PoW while training a global model across miners. It introduces a distributed evaluation protocol based on cross-miner predictions and a voting scheme to select top-K winners, whose local models are federated via FedAvg into a refreshed global model. A per-round reward mechanism quantifies each winner's contribution using a weight-difference metric $R_i = \frac{1}{L} \sum_{l} \frac{1}{N_l} \sum_{n} |W_n^{l} - \tilde{W}_n^{l}|$, ensuring fair compensation across rounds. Empirical results on CIFAR-10 with data-heterogeneous miners demonstrate robustness to attack scenarios (e.g., KNN-based strategies) and a reward distribution aligned with contribution, highlighting PoCL as a scalable, fair, and energy-efficient alternative for blockchain-enabled learning systems.

Abstract

Regardless of their variations, blockchains require a consensus mechanism to validate transactions, supervise added blocks, maintain network security, synchronize the network state, and distribute incentives. Proof-of-Work (PoW), one of the most influential implementations of consensus mechanisms, consumes an extraordinary amount of energy for a task that lacks direct productive output. In this paper, we propose Proof-of-Collaborative-Learning (PoCL), a multi-winner federated learning validated consensus mechanism that redirects the computation power of blockchains to train federated learning models. In addition, we present a novel evaluation mechanism to ensure the efficiency of the locally trained models of miners. We evaluated the security of our evaluation mechanism by introducing and conducting probable attacks. Moreover, we present a novel reward distribution mechanism to incentivize winning miners fairly, and demonstrate that our reward system is fair both within and across all rounds.

Figures (7)

• Figure 1: Proof-of-Collaborative-Learning (PoCL) Design.
• Figure 2: Network architecture
• Figure 3: The global model architecture.
• Figure 4: The relationship between data size, rewards, and the number of winning rounds.
• Figure 5: The winning miners for each mining round.