mlsanityData to 7 Oct 2026

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

arXiv 2210.00325 ↗First posted 1 Oct 2022cs.CR cs.LG cs.MAcited by 11

Not on the map. Why?

Abstract (arXiv)

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 the communication graph between the learners may vary between successive rounds of model aggregation. In particular, in each round of global model aggregation, the Metropolis-Hastings method is applied to update the weighted adjacency matrix based on the current communication topology. In addition, the Shamir's secret sharing scheme 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-word dataset.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 22 of its 79 references that are in the map. First posted on arXiv 1 Oct 2022.

Builds on

22 of 79 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  3. 2019Federated Learning for Wireless Communications: Motivation, Opportunities and Challengescited by 128
  4. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  5. 2019BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learningcited by 115
  6. 2019Peer-to-peer Federated Learning on Graphscited by 85
  7. 2019Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networkscited by 79
  8. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  9. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 72
  10. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  11. 2017Personalized and Private Peer-to-Peer Machine Learningcited by 54
  12. 2020Federated Learning in Vehicular Networkscited by 53
10 more
  1. 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43
  2. 2020POSEIDON: Privacy-Preserving Federated Neural Network Learningcited by 23
  3. 2021A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guaranteecited by 16
  4. 2020Privacy-preserving Decentralized Aggregation for Federated Learningcited by 10
  5. 2020Scalable Privacy-Preserving Distributed Learningcited by 9
  6. 2017Secure and Privacy-Preserving Consensuscited by 8
  7. 2018Tutorial on dynamic average consensus: the problem, its applications, and the algorithmscited by 8
  8. 2019Privacy-Preserving Average Consensus via State Decompositioncited by 8
  9. 2018Privacy preserving distributed optimization using homomorphic encryptioncited by 6
  10. 2015Differentially Private Average Consensus: Obstructions, Trade-Offs, and Optimal Algorithm Designcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 5; 2025: 1; 2026: 1.

11 papers.

  1. 2022A Survey on Over-the-Air Computationcited by 19
  2. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 16
  3. 2024Noiseless Privacy-Preserving Decentralized Learningcited by 9
  4. 2023On the Tradeoff between Privacy Preservation and Byzantine-Robustness in Decentralized Learningcited by 8
  5. 2023Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applicationscited by 3
  6. 2023SCoTTi: Save Computation at Training Time with an adaptive frameworkcited by 3
  7. 2024Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networkscited by 3
  8. 2024Swarm Learning: A Survey of Concepts, Applications, and Trendscited by 2
  9. 2024Fair Decentralized Learningcited by 1
  10. 2025ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learningcited by 0
  11. 2026Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneitiescited by 0