FedBGS: A Blockchain Approach to Segment Gossip Learning in Decentralized Systems

Privacy-Preserving Federated Learning (PPFL) is a Decentralized machine learning paradigm that enables multiple participants to collaboratively train a global model without sharing their data with the integration of cryptographic and privacy-based techniques to enhance the security of the global system. This privacy-oriented approach makes PPFL a highly suitable solution for training shared models in sectors where data privacy is a critical concern. In traditional FL, local models are trained on edge devices, and only model updates are shared with a central server, which aggregates them to improve the global model. However, despite the presence of the aforementioned privacy techniques, in the classical Federated structure, the issue of the server as a single-point-of-failure remains, leading to limitations both in terms of security and scalability. This paper introduces FedBGS, a fully Decentralized Blockchain-based framework that leverages Segmented Gossip Learning through Federated Analytics. The proposed system aims to optimize blockchain usage while providing comprehensive protection against all types of attacks, ensuring both privacy, security and non-IID data handling in Federated environments.

💡 Research Summary

**
FedBGS (Federated Blockchain Gossip Segmented) is a novel framework that tackles the three major shortcomings of conventional federated learning (FL): reliance on a central server, poor performance on non‑IID data, and the scalability constraints of blockchain‑based FL. The system integrates four key components. First, it employs one‑shot federated K‑Means++ clustering—an instance of federated analytics—to automatically group participants based on statistical summaries of their local data. The centroids are submitted to an Ethereum smart contract, which creates a permanent on‑chain mapping of each client to a cluster Cₖ. Second, the global model’s last fully‑connected layer is partitioned into K equal segments; each cluster is assigned a distinct segment