A Survey on Decentralized Federated Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910046617600000 |
|---|---|
| author | Gabrielli, Edoardo Di Pietro, Anthony Fenoglio, Dario Pica, Giovanni Tolomei, Gabriele |
| author_facet | Gabrielli, Edoardo Di Pietro, Anthony Fenoglio, Dario Pica, Giovanni Tolomei, Gabriele |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_04604 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Survey on Decentralized Federated Learning Gabrielli, Edoardo Di Pietro, Anthony Fenoglio, Dario Pica, Giovanni Tolomei, Gabriele Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing 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. |
| title | A Survey on Decentralized Federated Learning |
| topic | Machine Learning Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2308.04604 |