Trust-free Personalized Decentralized Learning

TL;DR

This paper introduces TPFed, a trust-free decentralized federated learning framework that uses blockchain and peer ranking to enable secure, personalized collaboration without central authorities, improving accuracy and robustness.

Contribution

We propose TPFed, a novel decentralized federated learning system that eliminates the need for trusted central servers using blockchain, peer ranking, and an all-in-one knowledge distillation protocol.

Findings

TBFed outperforms traditional federated learning in accuracy.

TBFed demonstrates robustness against adversarial attacks.

The blockchain-based design ensures secure, trust-free collaboration.

Abstract

Personalized collaborative learning in federated settings faces a critical trade-off between customization and participant trust. Existing approaches typically rely on centralized coordinators or trusted peer groups, limiting their applicability in open, trust-averse environments. While recent decentralized methods explore anonymous knowledge sharing, they often lack global scalability and robust mechanisms against malicious peers. To bridge this gap, we propose TPFed, a \textit{Trust-free Personalized Decentralized Federated Learning} framework. TPFed replaces central aggregators with a blockchain-based bulletin board, enabling participants to dynamically select global communication partners based on Locality-Sensitive Hashing (LSH) and peer ranking. Crucially, we introduce an ``all-in-one'' knowledge distillation protocol that simultaneously handles knowledge transfer, model quality evaluation, and similarity verification via a public reference dataset. This design ensures secure, globally personalized collaboration without exposing local models or data. Extensive experiments demonstrate that TPFed significantly outperforms traditional federated baselines in both learning accuracy and system robustness against adversarial attacks.