mlsanityData to 7 Oct 2026

Federated Meta-Learning with Fast Convergence and Efficient Communication

arXiv 1802.07876 ↗First posted 22 Feb 2018cs.LG cs.IRcited by 154

Not on the map. Why?

Abstract (arXiv)

Statistical and systematic challenges in collaboratively training machine learning models across distributed networks of mobile devices have been the bottlenecks in the real-world application of federated learning. In this work, we show that meta-learning is a natural choice to handle these issues, and propose a federated meta-learning framework FedMeta, where a parameterized algorithm (or meta-learner) is shared, instead of a global model in previous approaches. We conduct an extensive empirical evaluation on LEAF datasets and a real-world production dataset, and demonstrate that FedMeta achieves a reduction in required communication cost by 2.82-4.33 times with faster convergence, and an increase in accuracy by 3.23%-14.84% as compared to Federated Averaging (FedAvg) which is a leading optimization algorithm in federated learning. Moreover, FedMeta preserves user privacy since only the parameterized algorithm is transmitted between mobile devices and central servers, and no raw data is collected onto the servers.

Key facts. Cited by 154 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 37; 2023: 38; 2024: 22; 2025: 10; 2026: 9.

154 papers.

Sort:

By area:

  1. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  2. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  3. 2021A Field Guide to Federated Optimizationcited by 312
  4. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  5. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 180
  6. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  7. 2021Federated Graph Classification over Non-IID Graphscited by 113
  8. 2021Federated Reconstruction: Partially Local Federated Learningcited by 78
  9. 2022Personalized Federated Learning via Variational Bayesian Inferencecited by 68
  10. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  11. 2021What Do We Mean by Generalization in Federated Learning?cited by 62
  12. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
38 more
  1. 2021Cluster-driven Graph Federated Learning over Multiple Domainscited by 43
  2. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  3. 2022Test-Time Robust Personalization for Federated Learningcited by 39
  4. 2021Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspectivecited by 38
  5. 2023Eliminating Domain Bias for Federated Learning in Representation Spacecited by 38
  6. 2021Personalized Federated Learning: A Unified Framework and Universal Optimization Techniquescited by 34
  7. 2021FedGL: Federated Graph Learning Framework with Global Self-Supervisioncited by 34
  8. 2022On the Convergence of Clustered Federated Learningcited by 31
  9. 2022Motley: Benchmarking Heterogeneity and Personalization in Federated Learningcited by 31
  10. 2022Personalized Federated Learning With Graphcited by 29
  11. 2021Benchmarking Differential Privacy and Federated Learning for BERT Modelscited by 28
  12. 2022Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferringcited by 28
  13. 2021Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneitycited by 27
  14. 2021Federated Mixture of Expertscited by 27
  15. 2024FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuningcited by 27
  16. 2022CrowdGuard: Federated Backdoor Detection in Federated Learningcited by 26
  17. 2022A Survey on Federated Recommendation Systemscited by 25
  18. 2023Federated Domain Generalization: A Surveycited by 25
  19. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  20. 2023Semi-decentralized Federated Ego Graph Learning for Recommendationcited by 22
  21. 2021GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learningcited by 21
  22. 2021Federated Learning of Molecular Properties with Graph Neural Networks in a Heterogeneous Settingcited by 19
  23. 2023Dual Personalization on Federated Recommendationcited by 19
  24. 2024LightTR: A Lightweight Framework for Federated Trajectory Recoverycited by 19
  25. 2021Few-Shot Learning with Class Imbalancecited by 18
  26. 2023Achieving Linear Speedup in Non-IID Federated Bilevel Learningcited by 18
  27. 2023GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learningcited by 18
  28. 2021On Data Efficiency of Meta-learningcited by 16
  29. 2021FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognitioncited by 16
  30. 2023Visual Prompt Based Personalized Federated Learningcited by 16
  31. 2021On Bridging Generic and Personalized Federated Learning for Image Classificationcited by 15
  32. 2021A Non-parametric View of FedAvg and FedProx: Beyond Stationary Pointscited by 13
  33. 2021Efficient Federated Meta-Learning over Multi-Access Wireless Networkscited by 13
  34. 2022PGFed: Personalize Each Client's Global Objective for Federated Learningcited by 13
  35. 2021Compositional federated learning: Applications in distributionally robust averaging and meta learningcited by 12
  36. 2022FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphscited by 12
  37. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12
  38. 2024Advances in Robust Federated Learning: A Survey with Heterogeneity Considerationscited by 12

50 most cited of 154 All 154 (JSON)