mlsanityData to 7 Oct 2026

Ditto: Fair and Robust Federated Learning Through Personalization

arXiv 2012.04221 ↗First posted 8 Dec 2020cs.LG stat.MLcited by 665

Not on the map. Why?

Abstract (arXiv)

Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robustness simultaneously on a class of linear problems. Empirically, across a suite of federated datasets, we show that Ditto not only achieves competitive performance relative to recent personalization methods, but also enables more accurate, robust, and fair models relative to state-of-the-art fair or robust baselines.

Key facts. Cited by 665 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 48; 2022: 105; 2023: 135; 2024: 151; 2025: 130; 2026: 96.

665 papers.

Sort:

By area:

  1. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  2. 2021Towards Personalized Federated Learningcited by 462
  3. 2021A Field Guide to Federated Optimizationcited by 312
  4. 2021Federated Multi-Task Learning under a Mixture of Distributionscited by 189
  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. 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 146
  8. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  9. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
  10. 2024OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learningcited by 124
  11. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 121
  12. 2021Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learningcited by 116
38 more
  1. 2022Federated Learning with Partial Model Personalizationcited by 114
  2. 2021Federated Graph Classification over Non-IID Graphscited by 113
  3. 2021Parameterized Knowledge Transfer for Personalized Federated Learningcited by 108
  4. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  5. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  6. 2021FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Taskscited by 84
  7. 2022NVIDIA FLARE: Federated Learning from Simulation to Real-Worldcited by 78
  8. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  9. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 66
  10. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  11. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
  12. 2022Client Selection in Federated Learning: Principles, Challenges, and Opportunitiescited by 62
  13. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  14. 2021Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharingcited by 58
  15. 2021Towards Fairness-Aware Federated Learningcited by 57
  16. 2021Personalized Federated Learning through Local Memorizationcited by 57
  17. 2022FedAvg with Fine Tuning: Local Updates Lead to Representation Learningcited by 55
  18. 2023No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifiercited by 55
  19. 2021FedLab: A Flexible Federated Learning Frameworkcited by 54
  20. 2023Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generationcited by 54
  21. 2024Dual-Personalizing Adapter for Federated Foundation Modelscited by 54
  22. 2022FederatedScope: A Flexible Federated Learning Platform for Heterogeneitycited by 53
  23. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 50
  24. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  25. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
  26. 2022Orchestra: Unsupervised Federated Learning via Globally Consistent Clusteringcited by 45
  27. 2022Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learningcited by 45
  28. 2023Improving the Model Consistency of Decentralized Federated Learningcited by 45
  29. 2024Global and Local Prompts Cooperation via Optimal Transport for Federated Learningcited by 45
  30. 2022pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learningcited by 44
  31. 2022FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learningcited by 43
  32. 2022Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentationcited by 41
  33. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  34. 2021Improving Fairness via Federated Learningcited by 39
  35. 2022Test-Time Robust Personalization for Federated Learningcited by 39
  36. 2021Enforcing fairness in private federated learning via the modified method of differential multiplierscited by 38
  37. 2023Efficient Personalized Federated Learning via Sparse Model-Adaptationcited by 38
  38. 2023Eliminating Domain Bias for Federated Learning in Representation Spacecited by 38

50 most cited of 665 All 665 (JSON)