mlsanityData to 14 Oct 2026

Agnostic Federated Learning

arXiv 1902.00146 ↗First posted 1 Feb 2019cs.LG stat.MLcited by 456

Not on the map. Why?

Abstract (arXiv)

A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients. We argue that, with the existing training and inference, federated models can be biased towards different clients. Instead, we propose a new framework of agnostic federated learning, where the centralized model is optimized for any target distribution formed by a mixture of the client distributions. We further show that this framework naturally yields a notion of fairness. We present data-dependent Rademacher complexity guarantees for learning with this objective, which guide the definition of an algorithm for agnostic federated learning. We also give a fast stochastic optimization algorithm for solving the corresponding optimization problem, for which we prove convergence bounds, assuming a convex loss function and hypothesis set. We further empirically demonstrate the benefits of our approach in several datasets. Beyond federated learning, our framework and algorithm can be of interest to other learning scenarios such as cloud computing, domain adaptation, drifting, and other contexts where the training and test distributions do not coincide.

Key facts. Cited by 456 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 115; 2022: 91; 2023: 88; 2024: 67; 2025: 62; 2026: 33.

456 papers.

Sort:

By area:

  1. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  2. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
  3. 2021Towards Personalized Federated Learningcited by 464
  4. 2021A Field Guide to Federated Optimizationcited by 315
  5. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 192
  6. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  7. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  8. 2021Federated Learning for Open Bankingcited by 141
  9. 2021FairFed: Enabling Group Fairness in Federated Learningcited by 118
  10. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 109
  11. 2021FedMix: Approximation of Mixup under Mean Augmented Federated Learningcited by 108
  12. 2021Distributionally Robust Federated Averagingcited by 104
38 more
  1. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 101
  2. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  3. 2023Deep Model Fusion: A Surveycited by 91
  4. 2021Heterogeneity for the Win: One-Shot Federated Clusteringcited by 87
  5. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 84
  6. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
  7. 2021Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learningcited by 78
  8. 2021On Large-Cohort Training for Federated Learningcited by 74
  9. 2021FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learningcited by 69
  10. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 66
  11. 2021Provably Secure Federated Learning against Malicious Clientscited by 63
  12. 2021What Do We Mean by Generalization in Federated Learning?cited by 62
  13. 2021Federated Learning with Fair Averagingcited by 61
  14. 2022FedNest: Federated Bilevel, Minimax, and Compositional Optimizationcited by 60
  15. 2021Towards Fairness-Aware Federated Learningcited by 58
  16. 2021Personalized Federated Learning through Local Memorizationcited by 57
  17. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 52
  18. 2021Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learningcited by 50
  19. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  20. 2021FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusioncited by 49
  21. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  22. 2023Federated Conformal Predictors for Distributed Uncertainty Quantificationcited by 46
  23. 2021Cluster-driven Graph Federated Learning over Multiple Domainscited by 44
  24. 2021Unsupervised Learning of Debiased Representations with Pseudo-Attributescited by 44
  25. 2021On Tilted Losses in Machine Learning: Theory and Applicationscited by 43
  26. 2021Anarchic Federated Learningcited by 42
  27. 2022Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentationcited by 42
  28. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 41
  29. 2021Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementationcited by 40
  30. 2021Optimality and Stability in Federated Learning: A Game-theoretic Approachcited by 40
  31. 2023Improving Fairness in Deepfake Detectioncited by 40
  32. 2021AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learningcited by 39
  33. 2021Improving Fairness via Federated Learningcited by 39
  34. 2022Test-Time Robust Personalization for Federated Learningcited by 39
  35. 2022Mechanisms that Incentivize Data Sharing in Federated Learningcited by 39
  36. 2022On-Demand Sampling: Learning Optimally from Multiple Distributionscited by 39
  37. 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
  38. 2021Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspectivecited by 38

50 most cited of 456 All 456 (JSON)