BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning

By Abhijit Guha Roy, Shayan Siddiqui, Sebastian Pölsterl, Nassir Navab, Christian Wachinger. 2019

359 citations recorded by the source corpus.

Access to sufficient annotated data is a common challenge in training deep neural networks on medical images. As annotating data is expensive and time-consuming, it is difficult for an individual medical center to reach large enough sample sizes to build their own, personalized models. As an alternative, data from all centers could be pooled to train a centralized model that everyone can use. However, such a strategy is often infeasible due to the privacy-sensitive nature of medical data. Recently, federated learning (FL) has been introduced to collaboratively learn a shared prediction model across centers without the need for sharing data. In FL, clients are locally training models on site-specific datasets for a few epochs and then sharing their model weights with a central server, which orchestrates the overall training process. Importantly, the sharing of models does not compromise patient privacy. A disadvantage of FL is the dependence on a central server, which requires all clients to agree on one trusted central body, and whose failure would disrupt the training process of all clients. In this paper, we introduce BrainTorrent, a new FL framework without a central server, particularly targeted towards medical applications. BrainTorrent presents a highly dynamic peer-to-peer environment, where all centers directly interact with each other without depending on a central body. We demonstrate the overall effectiveness of FL for the challenging task of whole brain segmentation and observe that the proposed server-less BrainTorrent approach does not only outperform the traditional server-based one but reaches a similar performance to a model trained on pooled data.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lichao Sun
2. Ling Liu
3. Faisal Mahmood
4. Philip S. Yu
5. Bo Du
6. Mang Ye
7. Ming Y. Lu
8. Drew F. K. Williamson

Citations in the corpus

• Heterogeneous Federated Learning: State-of-the-art and Research Challenges (2023, background): “[176] propose a peer-to-peer federated learning framework without a central server, BrainTorrent, that is,”
• A Framework for Evaluating Gradient Leakage Attacks in Federated Learning (2020, background): “Finally, distributed training can happen in either federated scenario with a central server [22] or a decentralized scenario where clients are connected via a peer to peer network [33].”
• Federated Learning for Internet of Things: A Comprehensive Survey (2021, background): “A similar decentralized approach on a P2P network for federated healthcare is also studied in [126].”
• Decentralized Federated Learning: A Survey and Perspective (2023, background): “Roy et al. [169] introduced the BrainTorrent framework, in which a requesting client communicates with all clients to obtain information about available model versions, and clients with new versions send their models to the requesting client for aggregation.”
• Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges (2022, neutral): “BrainTorrent [148] is an FL framework without a central server explicitly aimed at medical applications.”
• Federated Learning for Healthcare: Systematic Review and Architecture Proposal (2022, methodology): “[46] employ the concept of BitTorrent swarms to distribute local model updates to all participants on an FL architecture.”
• Algorithm fairness in artificial intelligence for medicine and healthcare (2023, background): “…multi-institutional collaboration to aid the validation of AI algorithms for prostate segmentation, brain-cancer detection, the monitoring of the progression of Alzheimer’s disease using magnetic resonance imaging (MRI) and the classification of paediatric chest X-ray images 211,214,222–224 .”
• The future of digital health with federated learning (2020, background): “An example of this is peer-to-peer FL, where connections exist between all or a subset of the participants and model updates are shared only between directly-connected sites [37, 38].”
• A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning (2022, methodology): “Other P2P learning methods, such as graph based framework BrainTorrent [105] and Gossip Learning [46, 47] proposed their own solutions.”
• A Comprehensive Survey of Privacy-preserving Federated Learning (2021, background): “Compared to the client-server architecture, there is no central server [151, 214].”