BFLN: A Blockchain-based Federated Learning Model for Non-IID Data

TL;DR

The paper addresses non-IID data challenges in federated learning by proposing BFLN, a Blockchain-based Federated Learning Model for Non-IID Data. It combines a prototype-based aggregation (PAA) that uses prototype vectors and Pearson correlations with spectral clustering to create cluster-specific global models, and a cluster-centroid consensus (CACC) mechanism inspired by DPoS to ensure sustainable blockchain-based packaging and aggregation. An incentive scheme tied to cluster size (Gamma(n_i) = κ n_i^ρ) rewards participants proportionally to their cluster’s contribution, with hash-based verification to prevent fraud. Experiments on CIFAR10, CIFAR100, and SVHN show that BFLN outperforms baseline FL methods under various non-IID settings and demonstrates meaningful reward dynamics that encourage continued client participation and personalization.

Abstract

As the application of federated learning becomes increasingly widespread, the issue of imbalanced training data distribution has emerged as a significant challenge. Federated learning utilizes local data stored on different training clients for model training, rather than centralizing data on a server, thereby greatly enhancing the privacy and security of training data. However, the distribution of training data across different clients may be imbalanced, with different categories of data potentially residing on different clients. This presents a challenge to traditional federated learning, which assumes data distribution is independent and identically distributed (IID). This paper proposes a Blockchain-based Federated Learning Model for Non-IID Data (BFLN), which combines federated learning with blockchain technology. By introducing a new aggregation method and incentive algorithm, BFLN enhances the model performance of federated learning on non-IID data. Experiments on public datasets demonstrate that, compared to other state-of-the-art models, BFLN improves training accuracy and provides a sustainable incentive mechanism for personalized federated learning.

Figures (2)

• Figure 1: BFLN Model Structure
• Figure 2: BFLN Reward Trends and Different Local Training clients Cluster Summarize in Different Datasets