mlsanityData to 7 Oct 2026

On Bridging Generic and Personalized Federated Learning for Image Classification

arXiv 2107.00778 ↗First posted 2 Jul 2021cs.LG cs.AIcited by 15

Not on the map. Why?

Abstract (arXiv)

Federated learning is promising for its capability to collaboratively train models with multiple clients without accessing their data, but vulnerable when clients' data distributions diverge from each other. This divergence further leads to a dilemma: "Should we prioritize the learned model's generic performance (for future use at the server) or its personalized performance (for each client)?" These two, seemingly competing goals have divided the community to focus on one or the other, yet in this paper we show that it is possible to approach both at the same time. Concretely, we propose a novel federated learning framework that explicitly decouples a model's dual duties with two prediction tasks. On the one hand, we introduce a family of losses that are robust to non-identical class distributions, enabling clients to train a generic predictor with a consistent objective across them. On the other hand, we formulate the personalized predictor as a lightweight adaptive module that is learned to minimize each client's empirical risk on top of the generic predictor. With this two-loss, two-predictor framework which we name Federated Robust Decoupling (Fed-RoD), the learned model can simultaneously achieve state-of-the-art generic and personalized performance, essentially bridging the two tasks.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 87 of its 124 references that are in the map. First posted on arXiv 2 Jul 2021.

Builds on

87 of 124 references.

References · 87

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2019Advances and Open Problems in Federated Learningcited by 3,021
  7. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  8. 2019Invariant Risk Minimizationcited by 1,832
  9. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  10. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  11. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  12. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
38 more
  1. 2018Federated Learning with Non-IID Datacited by 1,099
  2. 2020Adaptive Federated Optimizationcited by 1,036
  3. 2016HyperNetworkscited by 1,003
  4. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  6. 2017A Survey on Multi-Task Learningcited by 838
  7. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  8. 2019Towards Federated Learning at Scale: System Designcited by 826
  9. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  10. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  11. 2018LEAF: A Benchmark for Federated Settingscited by 780
  12. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
  13. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  14. 2017Federated Multi-Task Learningcited by 669
  15. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  16. 2013Domain Generalization via Invariant Feature Representationcited by 622
  17. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  18. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  19. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
  20. 2020Federated Learning with Matched Averagingcited by 564
  21. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  22. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  23. 2019Federated Learning with Personalization Layerscited by 533
  24. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
  25. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  26. 2019Agnostic Federated Learningcited by 451
  27. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  28. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
  29. 2020Adaptive Personalized Federated Learningcited by 353
  30. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  31. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  32. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  33. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  34. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  35. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 282
  36. 2019Tighter Theory for Local SGD on Identical and Heterogeneous Datacited by 266
  37. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  38. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253

50 most cited of 87 All 87 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 5; 2024: 3; 2025: 1.

15 papers.

Sort:

  1. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  2. 2022DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Trainingcited by 74
  3. 2022Test-Time Robust Personalization for Federated Learningcited by 39
  4. 2022FedTP: Federated Learning by Transformer Personalizationcited by 36
  5. 2023Privacy and Fairness in Federated Learning: on the Perspective of Trade-offcited by 26
  6. 2021Towards Federated Learning on Time-Evolving Heterogeneous Datacited by 23
  7. 2022Accelerated Federated Learning with Decoupled Adaptive Optimizationcited by 23
  8. 2021FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognitioncited by 16
  9. 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
  10. 2023pFedSim: Similarity-Aware Model Aggregation Towards Personalized Federated Learningcited by 9
  11. 2024MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classescited by 7
  12. 2023Medical Federated Model with Mixture of Personalized and Sharing Componentscited by 1
3 more
  1. 2025FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID Datacited by 1
  2. 2023Global Layers: Non-IID Tabular Federated Learningcited by 0
  3. 2024EPIC: Enhancing Privacy through Iterative Collaborationcited by 0