DFPL: Decentralized Federated Prototype Learning Across Heterogeneous Data Distributions

TL;DR

This paper introduces DFPL, a decentralized federated learning framework that leverages prototype learning and blockchain to enhance performance and communication efficiency in heterogeneous data environments.

Contribution

DFPL integrates prototype learning into decentralized federated learning and embeds blockchain to improve performance and reduce communication overhead under data heterogeneity.

Findings

DFPL outperforms existing methods in model accuracy.

DFPL reduces communication costs significantly.

DFPL demonstrates robust convergence properties.

Abstract

Federated learning is a distributed machine learning paradigm through centralized model aggregation. However, standard federated learning relies on a centralized server, making it vulnerable to server failures. While existing solutions utilize blockchain technology to implement Decentralized Federated Learning (DFL), the statistical heterogeneity of data distributions among clients severely degrades the performance of DFL. Driven by this issue, this paper proposes a decentralized federated prototype learning framework, named DFPL, which significantly improves the performance of DFL under heterogeneous data distributions. Specifically, DFPL introduces prototype learning into DFL to mitigate the impact of statistical heterogeneity and reduces the amount of parameters exchanged between clients. Additionally, blockchain is embedded into our framework, enabling the training and mining processes to be executed locally on each client. From a theoretical perspective, we analyze the convergence of DFPL by modeling the required computational resources during both training and mining. The experiment results highlight the superiority of DFPL in both model performance and communication efficiency across four benchmark datasets with heterogeneous data distributions.