mlsanityData to 14 Oct 2026

Test-Time Robust Personalization for Federated Learning

arXiv 2205.10920 ↗First posted 22 May 2022cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a machine learning paradigm where many clients collaboratively learn a shared global model with decentralized training data. Personalized FL additionally adapts the global model to different clients, achieving promising results on consistent local training and test distributions. However, for real-world personalized FL applications, it is crucial to go one step further: robustifying FL models under the evolving local test set during deployment, where various distribution shifts can arise. In this work, we identify the pitfalls of existing works under test-time distribution shifts and propose Federated Test-time Head Ensemble plus tuning(FedTHE+), which personalizes FL models with robustness to various test-time distribution shifts. We illustrate the advancement of FedTHE+ (and its computationally efficient variant FedTHE) over strong competitors, by training various neural architectures (CNN, ResNet, and Transformer) on CIFAR10 andImageNet with various test distributions. Along with this, we build a benchmark for assessing the performance and robustness of personalized FL methods during deployment. Code: https://github.com/LINs-lab/FedTHE.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 90 of its 121 references that are in the map. First posted on arXiv 22 May 2022.

Builds on

90 of 121 references.

References · 90

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  8. 2016Layer Normalizationcited by 5,669
  9. 2019Advances and Open Problems in Federated Learningcited by 3,046
  10. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  11. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  12. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
38 more
  1. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  2. 2019Invariant Risk Minimizationcited by 1,854
  3. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2018Group Normalizationcited by 1,524
  6. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  8. 2019Natural Adversarial Examplescited by 1,408
  9. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  10. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  11. 2020In Search of Lost Domain Generalizationcited by 1,054
  12. 2020Adaptive Federated Optimizationcited by 1,046
  13. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  14. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  15. 2021Robust fine-tuning of zero-shot modelscited by 797
  16. 2018LEAF: A Benchmark for Federated Settingscited by 792
  17. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  18. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  19. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  20. 2017Federated Multi-Task Learningcited by 672
  21. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  22. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  23. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  24. 2019Federated Learning with Personalization Layerscited by 541
  25. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
  26. 2022Continual Test-Time Domain Adaptationcited by 525
  27. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  28. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  29. 2021Towards Personalized Federated Learningcited by 464
  30. 2019Agnostic Federated Learningcited by 456
  31. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 454
  32. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  33. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
  34. 2019Fair Resource Allocation in Federated Learningcited by 394
  35. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  36. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  37. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  38. 2020Adaptive Personalized Federated Learningcited by 358

50 most cited of 90 All 90 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 17; 2024: 7; 2025: 10; 2026: 3.

39 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  2. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  3. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 84
  4. 2023On Pitfalls of Test-Time Adaptationcited by 64
  5. 2024Dual-Personalizing Adapter for Federated Foundation Modelscited by 55
  6. 2022FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reductioncited by 35
  7. 2023Adaptive Test-Time Personalization for Federated Learningcited by 23
  8. 2024PuzzleAvatar: Assembling 3D Avatars from Personal Albumscited by 16
  9. 2023FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clusteringcited by 15
  10. 2023PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guaranteescited by 15
  11. 2024FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detectioncited by 14
  12. 2025FedRSClip: Federated Learning for Remote Sensing Scene Classification Using Vision-Language Modelscited by 11
27 more
  1. 2022Straggler-Resilient Personalized Federated Learningcited by 9
  2. 2023Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuningcited by 9
  3. 2023ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learningcited by 9
  4. 2025Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learningcited by 9
  5. 2023FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learningcited by 5
  6. 2023Combating Exacerbated Heterogeneity for Robust Models in Federated Learningcited by 4
  7. 2023Federated Continual Novel Class Learningcited by 4
  8. 2023Cooperative Hardware-Prompt Learning for Snapshot Compressive Imagingcited by 3
  9. 2023UPFL: Unsupervised Personalized Federated Learning towards New Clientscited by 3
  10. 2023Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologiescited by 3
  11. 2023An Empirical Evaluation of Federated Contextual Bandit Algorithmscited by 2
  12. 2024Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switchingcited by 2
  13. 2024ProFL: Performative Robust Optimal Federated Learningcited by 2
  14. 2025Federated Adapter on Foundation Models: An Out-Of-Distribution Approachcited by 2
  15. 2025FedCTTA: A Collaborative Approach to Continual Test-Time Adaptation in Federated Learningcited by 2
  16. 2025FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Modelscited by 2
  17. 2024Friends in Unexpected Places: Enhancing Local Fairness in Federated Learning through Clusteringcited by 1
  18. 2025pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Datacited by 1
  19. 2023Global Layers: Non-IID Tabular Federated Learningcited by 0
  20. 2024Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexingcited by 0
  21. 2025BTFL: A Bayesian-based Test-Time Generalization Method for Internal and External Data Distributions in Federated learningcited by 0
  22. 2025Query-based Knowledge Transfer for Heterogeneous Learning Environmentscited by 0
  23. 2025ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoningcited by 0
  24. 2025FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OODcited by 0
  25. 2026Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learningcited by 0
  26. 2026HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learningcited by 0
  27. 2026FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Modelscited by 0