A Survey on Decentralized Federated Learning

TL;DR

This survey reviews decentralized federated learning methods, highlighting their architectures, challenges, evaluation practices, and future research directions in privacy, security, and incentive mechanisms.

Contribution

It provides a unified taxonomy of DFL methods, analyzes evaluation gaps, and outlines key research challenges in topology-aware security, privacy, and personalization.

Findings

DFL methods are categorized into traditional distributed and blockchain-based approaches.

Current evaluation practices have notable limitations and gaps.

Future research should focus on topology-aware threat models and personalized solutions.

Abstract

Federated learning (FL) enables collaborative training without pooling raw data, but standard FL relies on a central coordinator, which introduces a single point of failure and concentrates trust in the orchestration infrastructure. Decentralized federated learning (DFL) removes the coordinator and replaces client-server orchestration with peer-to-peer coordination, making learning dynamics topology-dependent and reshaping the associated security, privacy, and systems trade-offs. This survey systematically reviews DFL methods from 2018 through early 2026 and organizes them into two architectural families: traditional distributed FL and blockchain-based FL. We then propose a unified, challenge-driven taxonomy that maps both families to the core bottlenecks they primarily address, and we summarize prevailing evaluation practices and their limitations, exposing gaps in the literature. Finally, we distill lessons learned and outline research directions, emphasizing topology-aware threat models, privacy notions that reflect decentralized exposure, incentive mechanisms robust to manipulation, and the need to explicitly define whether the objective is a single global model or personalized solutions in decentralized settings.