mlsanityData to 7 Oct 2026

Federated Learning via Inexact ADMM

arXiv 2204.10607 ↗First posted 22 Apr 2022math.OC cs.LGcited by 44

Not on the map. Why?

Abstract (arXiv)

One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full device participation and/or impose strong assumptions for convergence. Different from the widely-used gradient descent-based algorithms, in this paper, we develop an inexact alternating direction method of multipliers (ADMM), which is both computation- and communication-efficient, capable of combating the stragglers' effect, and convergent under mild conditions. Furthermore, it has a high numerical performance compared with several state-of-the-art algorithms for federated learning.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 40 of its 58 references that are in the map. First posted on arXiv 22 Apr 2022.

Builds on

40 of 58 references.

References · 40

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  6. 2020The Future of Digital Health with Federated Learningcited by 625
  7. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  8. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  9. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  10. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  11. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  12. 2018Sparsified SGD with Memorycited by 373
28 more
  1. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 277
  2. 2018Federated Learning via Over-the-Air Computationcited by 215
  3. 2018Don't Use Large Mini-Batches, Use Local SGDcited by 201
  4. 2017Gradient Sparsification for Communication-Efficient Distributed Optimizationcited by 199
  5. 2015Federated Optimization:Distributed Optimization Beyond the Datacentercited by 193
  6. 2020FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Datacited by 143
  7. 2022Federated Learning with Partial Model Personalizationcited by 114
  8. 2016Asynchronous Stochastic Gradient Descent with Delay Compensationcited by 98
  9. 2018LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learningcited by 95
  10. 2014Deep learning with Elastic Averaging SGDcited by 90
  11. 2021Federated Reconstruction: Partially Local Federated Learningcited by 78
  12. 2016CoCoA: A General Framework for Communication-Efficient Distributed Optimizationcited by 69
  13. 2020Federated Learning in Vehicular Networkscited by 53
  14. 2018DP-ADMM: ADMM-based Distributed Learning with Differential Privacycited by 41
  15. 2021Personalized Federated Learning: A Unified Framework and Universal Optimization Techniquescited by 34
  16. 2020Federated Learning and Wireless Communicationscited by 27
  17. 2020Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learningcited by 22
  18. 2018Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithmscited by 20
  19. 2021Communication-Efficient ADMM-based Federated Learningcited by 14
  20. 2021Differentially Private Federated Learning via Inexact ADMMcited by 11
  21. 2020Federated Nonconvex Sparse Learningcited by 10
  22. 2019L-FGADMM: Layer-Wise Federated Group ADMM for Communication Efficient Decentralized Deep Learningcited by 8
  23. 2018Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithmscited by 7
  24. 2015Fast ADMM Algorithm for Distributed Optimization with Adaptive Penaltycited by 6
  25. 2020Decentralized Learning with Lazy and Approximate Dual Gradientscited by 6
  26. 2020Communication Efficient Distributed Learning with Censored, Quantized, and Generalized Group ADMMcited by 6
  27. 2017Robust Decentralized Learning Using ADMM with Unreliable Agentscited by 5
  28. 2022A dual approach for federated learningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 13; 2024: 13; 2025: 9; 2026: 6.

44 papers.

Sort:

By area:

  1. 2023Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initializationcited by 21
  2. 2022FedGiA: An Efficient Hybrid Algorithm for Federated Learningcited by 8
  3. 2023DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learningcited by 6
  4. 2025Knowledge Adaptation as Posterior Correctioncited by 6
  5. 2023From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learningcited by 5
  6. 2023Asymmetrically Decentralized Federated Learningcited by 5
  7. 2024Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Surveycited by 5
  8. 2023Personalized Graph Federated Learning with Differential Privacycited by 4
  9. 2023Federated Learning with Convex Global and Local Constraintscited by 4
  10. 2024FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learningcited by 4
  11. 2024Hierarchical Federated ADMMcited by 4
  12. 2025Connecting Federated ADMM to Bayescited by 4
32 more
  1. 2025FedCanon: Non-Convex Composite Federated Learning with Efficient Proximal Operation on Heterogeneous Datacited by 4
  2. 2022Federated Learning Using Three-Operator ADMMcited by 3
  3. 2023Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMMcited by 3
  4. 2023Federated Reinforcement Learning for Resource Allocation in V2X Networkscited by 3
  5. 2024Distributed Event-Based Learning via ADMMcited by 3
  6. 2024Review of Mathematical Optimization in Federated Learningcited by 3
  7. 2025Federated ADMM from Bayesian Dualitycited by 3
  8. 2023Sparse Decentralized Federated Learningcited by 2
  9. 2023Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsificationcited by 2
  10. 2024A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needscited by 2
  11. 2024Boosting the Performance of Decentralized Federated Learning via Catalyst Accelerationcited by 2
  12. 2025Preconditioned Inexact Stochastic ADMM for Deep Modelcited by 2
  13. 2022Exact Penalty Method for Federated Learningcited by 1
  14. 2023PPFL: A Personalized Federated Learning Framework for Heterogeneous Populationcited by 1
  15. 2024BADM: Batch ADMM for Deep Learningcited by 1
  16. 2024FedSat: A Statistical Aggregation Approach for Class Imbalanced Clients in Federated Learningcited by 1
  17. 2024Noise-Robust and Resource-Efficient ADMM-based Federated Learningcited by 1
  18. 2024OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancementcited by 1
  19. 2024Controlling Participation in Federated Learning with Feedbackcited by 1
  20. 2025Distributed optimization: designed for federated learningcited by 1
  21. 2026Decentralized Federated Learning by Partial Message Exchangecited by 1
  22. 2023CRS-FL: Conditional Random Sampling for Communication-Efficient and Privacy-Preserving Federated Learningcited by 0
  23. 2023Personalized Federated Learning via ADMM with Moreau Envelopecited by 0
  24. 2024On ADMM in Heterogeneous Federated Learning: Personalization, Robustness, and Fairnesscited by 0
  25. 2025On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimizationcited by 0
  26. 2025A Linearized Alternating Direction Multiplier Method for Federated Matrix Completion Problemscited by 0
  27. 2025DHO2: Accelerating Distributed Hybrid Order Optimization via Model Parallelism and ADMMcited by 0
  28. 2026Event-Triggered Gossip for Distributed Learningcited by 0
  29. 2026First-Order Softmax Weighted Switching Gradient Method for Distributed Stochastic Minimax Optimization with Stochastic Constraintscited by 0
  30. 2026Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalizationcited by 0
  31. 2026Function-Space ADMM for Decentralized Federated Learning: A Control Theoretic Perspectivecited by 0
  32. 2026Co-VLA: Consensus-based Federated Training for Vision-Language-Action Modelscited by 0