Wait or Not to Wait: Evaluating Trade-Offs between Speed and Precision in Blockchain-based Federated Aggregation

TL;DR

This paper introduces a blockchain-based federated learning system that decentralizes training and aggregation, enhancing trust, flexibility, and efficiency, with experimental validation showing comparable accuracy to centralized methods and benefits of asynchronous aggregation for simple models.

Contribution

The work presents a fully decentralized blockchain-assisted federated learning architecture with flexible model selection and aggregation methods, validated through real-world Ethereum deployments.

Findings

Decentralized federated learning achieves similar accuracy to centralized systems.

Asynchronous aggregation is effective for simple models.

Flexible model selection reduces communication round time.

Abstract

This paper presents a fully coupled blockchain-assisted federated learning architecture that effectively eliminates single points of failure by decentralizing both the training and aggregation tasks across all participants. Our proposed system offers a high degree of flexibility, allowing participants to select shared models and customize the aggregation for local needs, thereby optimizing system performance, including accurate inference results. Notably, the integration of blockchain technology in our work is to promote a trustless environment, ensuring transparency and non-repudiation among participants when abnormalities are detected. To validate the effectiveness, we conducted real-world federated learning deployments on a private Ethereum platform, using two different models, ranging from simple to complex neural networks. The experimental results indicate comparable inference accuracy between centralized and decentralized federated learning settings. Furthermore, our findings indicate that asynchronous aggregation is a feasible option for simple learning models. However, complex learning models require greater training model involvement in the aggregation to achieve high model quality, instead of asynchronous aggregation. With the implementation of asynchronous aggregation and the flexibility to select models, participants anticipate decreased aggregation time in each communication round, while experiencing minimal accuracy trade-off.