Home > Research > Publications & Outputs > Privacy-preserving Decentralized Federated Lear...

Electronic data

  • 3591354

    Accepted author manuscript, 2.19 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License


Text available via DOI:

View graph of relations

Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Article number33
<mark>Journal publication date</mark>31/08/2023
<mark>Journal</mark>ACM Transactions on Privacy and Security
Issue number3
Number of pages39
Pages (from-to)1-39
Publication StatusPublished
Early online date6/04/23
<mark>Original language</mark>English


Establishing how a set of learners can provide privacy-preserving federated learning in a fully decentralized (peer-to-peer, no coordinator) manner is an open problem. We propose the first privacy-preserving consensus-based algorithm for the distributed learners to achieve decentralized global model aggregation in an environment of high mobility, where participating learners and the communication graph between them may vary during the learning process. In particular, whenever the communication graph changes, the Metropolis-Hastings method [69] is applied to update the weighted adjacency matrix based on the current communication topology. In addition, the Shamir’s secret sharing scheme [61] is integrated to facilitate privacy in reaching consensus of the global model. The paper establishes the correctness and privacy properties of the proposed algorithm. The computational efficiency is evaluated by a simulation built on a federated learning framework with a real-world dataset.