mlsanityData to 7 Oct 2026

Communication-Efficient ADMM-based Federated Learning

arXiv 2110.15318 ↗First posted 28 Oct 2021cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Federated learning has shown its advances over the last few years but is facing many challenges, such as how algorithms save communication resources, how they reduce computational costs, and whether they converge. To address these issues, this paper proposes exact and inexact ADMM-based federated learning. They are not only communication-efficient but also converge linearly under very mild conditions, such as convexity-free and irrelevance to data distributions. Moreover, the inexact version has low computational complexity, thereby alleviating the computational burdens significantly.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 28 Oct 2021.

Builds on

27 of 42 references.

References · 27

  1. 2019Advances and Open Problems in Federated Learningcited by 3,021
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  3. 2020The Future of Digital Health with Federated Learningcited by 625
  4. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  5. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  6. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  7. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
  8. 2018Federated Learning via Over-the-Air Computationcited by 215
  9. 2018Don't Use Large Mini-Batches, Use Local SGDcited by 201
  10. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 193
  11. 2016Asynchronous Stochastic Gradient Descent with Delay Compensationcited by 98
  12. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 95
15 more
  1. 2014Deep learning with Elastic Averaging SGDcited by 90
  2. 2020Federated Learning in Vehicular Networkscited by 53
  3. 2017Mobile Edge Computing: A Survey on Architecture and Computation Offloadingcited by 52
  4. 2018DP-ADMM: ADMM-based Distributed Learning with Differential Privacycited by 41
  5. 2020Federated Learning and Wireless Communicationscited by 27
  6. 2020Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learningcited by 22
  7. 2018Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithmscited by 20
  8. 2020Communication-Efficient Massive UAV Online Path Control: Federated Learning Meets Mean-Field Game Theorycited by 16
  9. 2021Differentially Private Federated Learning via Inexact ADMMcited by 11
  10. 2020Federated Nonconvex Sparse Learningcited by 10
  11. 2019L-FGADMM: Layer-Wise Federated Group ADMM for Communication Efficient Decentralized Deep Learningcited by 8
  12. 2015Fast ADMM Algorithm for Distributed Optimization with Adaptive Penaltycited by 6
  13. 2020Decentralized Learning with Lazy and Approximate Dual Gradientscited by 6
  14. 2020Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMMcited by 6
  15. 2017Robust Decentralized Learning Using ADMM with Unreliable Agentscited by 5

Built on by

Cited by year

Citing papers per year: 2022: 8; 2023: 3; 2024: 2; 2025: 1.

14 papers.

Sort:

  1. 2022Federated Learning via Inexact ADMMcited by 44
  2. 2022APPFL: Open-Source Software Framework for Privacy-Preserving Federated Learningcited by 20
  3. 2024Advances in APPFL: A Comprehensive and Extensible Federated Learning Frameworkcited by 19
  4. 2022Distributed Learning With Sparsified Gradient Differencescited by 9
  5. 2022Confederated Learning: Federated Learning with Decentralized Edge Serverscited by 7
  6. 2023Advancements in Federated Learning: Models, Methods, and Privacycited by 7
  7. 2022Federated Learning Using Three-Operator ADMMcited by 3
  8. 2023Federated Reinforcement Learning for Resource Allocation in V2X Networkscited by 3
  9. 2024Federated PCA on Grassmann Manifold for IoT Anomaly Detectioncited by 3
  10. 2022Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMOcited by 2
  11. 2022Exact Penalty Method for Federated Learningcited by 1
  12. 2022Differentially Private Federated Learning via Inexact ADMM with Multiple Local Updatescited by 0
2 more
  1. 2023Differentially Private Distributed Convex Optimizationcited by 0
  2. 2025Communication-Efficient Distributed Asynchronous ADMMcited by 0