mlsanityData to 14 Oct 2026

Semi-Decentralized Federated Learning with Collaborative Relaying

arXiv 2205.10998 ↗First posted 23 May 2022cs.LG cs.DC cs.MAcited by 16

Not on the map. Why?

Abstract (arXiv)

We present a semi-decentralized federated learning algorithm wherein clients collaborate by relaying their neighbors' local updates to a central parameter server (PS). At every communication round to the PS, each client computes a local consensus of the updates from its neighboring clients and eventually transmits a weighted average of its own update and those of its neighbors to the PS. We appropriately optimize these averaging weights to ensure that the global update at the PS is unbiased and to reduce the variance of the global update at the PS, consequently improving the rate of convergence. Numerical simulations substantiate our theoretical claims and demonstrate settings with intermittent connectivity between the clients and the PS, where our proposed algorithm shows an improved convergence rate and accuracy in comparison with the federated averaging algorithm.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 42 of its 51 references that are in the map. First posted on arXiv 23 May 2022.

Builds on

42 of 51 references.

References · 42

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Learning with Non-IID Datacited by 1,108
  3. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  4. 2017Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descentcited by 502
  5. 2020A Unified Theory of Decentralized SGD with Changing Topology and Local Updatescited by 367
  6. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
  7. 2019Client-Edge-Cloud Hierarchical Federated Learningcited by 202
  8. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 193
  9. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  10. 2019Federated Learning over Wireless Fading Channelscited by 183
  11. 2013On the Convergence of Decentralized Gradient Descentcited by 159
  12. 2018Stochastic Gradient Push for Distributed Deep Learningcited by 152
30 more
  1. 2018D2: Decentralized Training over Decentralized Datacited by 140
  2. 2019Scheduling Policies for Federated Learning in Wireless Networkscited by 131
  3. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
  4. 2020Federated Visual Classification with Real-World Data Distributioncited by 128
  5. 2019Hierarchical Federated Learning Across Heterogeneous Cellular Networkscited by 98
  6. 2021Fast Federated Learning in the Presence of Arbitrary Device Unavailabilitycited by 72
  7. 2020Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edgecited by 71
  8. 2019MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Samplingcited by 67
  9. 2017Collaborative Deep Learning in Fixed Topology Networkscited by 60
  10. 2020Multi-Armed Bandit Based Client Scheduling for Federated Learningcited by 57
  11. 2021Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregationscited by 51
  12. 2021Consensus Control for Decentralized Deep Learningcited by 49
  13. 2019Device Scheduling with Fast Convergence for Wireless Federated Learningcited by 46
  14. 2016On Nonconvex Decentralized Gradient Descentcited by 42
  15. 2019Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networkscited by 39
  16. 2021RelaySum for Decentralized Deep Learning on Heterogeneous Datacited by 39
  17. 2018Efficient Decentralized Deep Learning by Dynamic Model Averagingcited by 30
  18. 2013Millimeter Wave Channel Modeling and Cellular Capacity Evaluationcited by 29
  19. 2020Communicate to Learn at the Edgecited by 28
  20. 2021Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregationcited by 22
  21. 2019Data-Importance Aware User Scheduling for Communication-Efficient Edge Machine Learningcited by 20
  22. 2020Decentralized SGD with Over-the-Air Computationcited by 16
  23. 2020Private Wireless Federated Learning with Anonymous Over-the-Air Computationcited by 16
  24. 2020Decentralized optimization over noisy, rate-constrained networks: Achieving consensus by communicating differencescited by 12
  25. 2021Fast Federated Edge Learning with Overlapped Communication and Computation and Channel-Aware Fair Client Schedulingcited by 9
  26. 2017On the Temporal Effects of Mobile Blockers in Urban Millimeter-Wave Cellular Scenarioscited by 5
  27. 2022Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relayingcited by 5
  28. 2020Exploiting Local and Cloud Sensor Fusion in Intermittently Connected Sensor Networkscited by 4
  29. 2021Cloud-Cluster Architecture for Detection in Intermittently Connected Sensor Networkscited by 4
  30. 2021Collaborative Learning over Wireless Networks: An Introductory Overviewcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 3; 2025: 2; 2026: 3.

16 papers.

Sort:

  1. 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
  2. 2022A Survey on Over-the-Air Computationcited by 21
  3. 2022Non-Coherent Over-the-Air Decentralized Gradient Descentcited by 9
  4. 2023A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learningcited by 3
  5. 2023Enhancing Scalability and Reliability in Semi-Decentralized Federated Learning With Blockchain: Trust Penalization and Asynchronous Functionalitycited by 3
  6. 2023Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacycited by 2
  7. 2024Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networkscited by 2
  8. 2024UAV-assisted Unbiased Hierarchical Federated Learning: Performance and Convergence Analysiscited by 2
  9. 2023Joint Client Assignment and UAV Route Planning for Indirect-Communication Federated Learningcited by 1
  10. 2026Centralized vs Decentralized Federated Learning: A trade-off performance analysiscited by 1
  11. 2026Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missionscited by 1
  12. 2023FedDec: Peer-to-peer Aided Federated Learningcited by 0
4 more
  1. 2024TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learningcited by 0
  2. 2025Semi-decentralized Federated Time Series Prediction with Client Availability Budgetscited by 0
  3. 2025From Federated Learning to X-Learning: Breaking the Barriers of Decentrality Through Random Walkscited by 0
  4. 2026Towards Serverless Semi-Decentralized Federated Learning with Heterogeneous Optimizerscited by 0