mlsanityData to 7 Oct 2026

FedBABU: Towards Enhanced Representation for Federated Image Classification

arXiv 2106.06042 ↗First posted 4 Jun 2021cs.LGcited by 180

Not on the map. Why?

Abstract (arXiv)

Federated learning has evolved to improve a single global model under data heterogeneity (as a curse) or to develop multiple personalized models using data heterogeneity (as a blessing). However, little research has considered both directions simultaneously. In this paper, we first investigate the relationship between them by analyzing Federated Averaging at the client level and determine that a better federated global model performance does not constantly improve personalization. To elucidate the cause of this personalization performance degradation problem, we decompose the entire network into the body (extractor), which is related to universality, and the head (classifier), which is related to personalization. We then point out that this problem stems from training the head. Based on this observation, we propose a novel federated learning algorithm, coined FedBABU, which only updates the body of the model during federated training (i.e., the head is randomly initialized and never updated), and the head is fine-tuned for personalization during the evaluation process. Extensive experiments show consistent performance improvements and an efficient personalization of FedBABU. The code is available at https://github.com/jhoon-oh/FedBABU.

Key facts. Cited by 180 papers in the map (data through 7 Oct 2026). Builds on 45 of its 64 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

45 of 64 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  8. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  10. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  11. 2014How transferable are features in deep neural networks?cited by 1,216
  12. 2018Federated Learning with Non-IID Datacited by 1,099
33 more
  1. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  2. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  3. 2019A Closer Look at Few-shot Classificationcited by 679
  4. 2017Federated Multi-Task Learningcited by 669
  5. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  6. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  7. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  8. 2019Federated Learning with Personalization Layerscited by 533
  9. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  10. 2021Towards Personalized Federated Learningcited by 462
  11. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  12. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  13. 2020Adaptive Personalized Federated Learningcited by 353
  14. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  15. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 321
  16. 2020Personalized Federated Learning: A Meta-Learning Approachcited by 309
  17. 2019A Baseline for Few-Shot Image Classificationcited by 298
  18. 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 264
  19. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
  20. 2021Personalized Federated Learning using Hypernetworkscited by 210
  21. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  22. 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
  23. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  24. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 154
  25. 2019Federated Evaluation of On-device Personalizationcited by 147
  26. 2020Survey of Personalization Techniques for Federated Learningcited by 144
  27. 2019Meta-Learning with Warped Gradient Descentcited by 98
  28. 2019Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applicationscited by 64
  29. 2020Performance Optimization for Federated Person Re-identification via Benchmark Analysiscited by 50
  30. 2017OL'E: Orthogonal Low-rank Embedding, A Plug and Play Geometric Loss for Deep Learningcited by 37
  31. 2021Emerging Trends in Federated Learning: From Model Fusion to Federated X Learningcited by 35
  32. 2019Modular Meta-Learning with Shrinkagecited by 31
  33. 2020The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysiscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 18; 2023: 41; 2024: 50; 2025: 35; 2026: 34.

180 papers.

Sort:

By area:

  1. 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
  2. 2023Deep Model Fusion: A Surveycited by 89
  3. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 66
  4. 2023FedGH: Heterogeneous Federated Learning with Generalized Global Headercited by 56
  5. 2022FedAvg with Fine Tuning: Local Updates Lead to Representation Learningcited by 55
  6. 2021FedLab: A Flexible Federated Learning Frameworkcited by 54
  7. 2023Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generationcited by 54
  8. 2024Global and Local Prompts Cooperation via Optimal Transport for Federated Learningcited by 45
  9. 2022pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learningcited by 44
  10. 2023Eliminating Domain Bias for Federated Learning in Representation Spacecited by 38
  11. 2024FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuningcited by 27
  12. 2024Harmonizing Generalization and Personalization in Federated Prompt Learningcited by 26
38 more
  1. 2022FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentationcited by 24
  2. 2022Accelerated Federated Learning with Decoupled Adaptive Optimizationcited by 23
  3. 2023Adaptive Test-Time Personalization for Federated Learningcited by 23
  4. 2022Gradient Masked Averaging for Federated Learningcited by 22
  5. 2023FS-Real: Towards Real-World Cross-Device Federated Learningcited by 22
  6. 2023Layer-wise Linear Mode Connectivitycited by 22
  7. 2022IOP-FL: Inside-Outside Personalization for Federated Medical Image Segmentationcited by 21
  8. 2023FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learningcited by 21
  9. 2024Federated Model Heterogeneous Matryoshka Representation Learningcited by 21
  10. 2023Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learningcited by 20
  11. 2022SphereFed: Hyperspherical Federated Learningcited by 19
  12. 2023FedHCA2: Towards Hetero-Client Federated Multi-Task Learningcited by 17
  13. 2023Visual Prompt Based Personalized Federated Learningcited by 16
  14. 2023FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolationcited by 14
  15. 2023FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learningcited by 14
  16. 2024Federated Graph Learning with Structure Proxy Alignmentcited by 14
  17. 2022PGFed: Personalize Each Client's Global Objective for Federated Learningcited by 13
  18. 2023Re-thinking Federated Active Learning based on Inter-class Diversitycited by 13
  19. 2024Federated Learning with Bilateral Curation for Partially Class-Disjoint Datacited by 13
  20. 2024Personalized Federated Learning via Feature Distribution Adaptationcited by 13
  21. 2023FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learningcited by 10
  22. 2024FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Datacited by 10
  23. 2024Accelerating Heterogeneous Federated Learning with Closed-form Classifierscited by 10
  24. 2023FedDWA: Personalized Federated Learning with Dynamic Weight Adjustmentcited by 9
  25. 2023pFedSim: Similarity-Aware Model Aggregation Towards Personalized Federated Learningcited by 9
  26. 2023ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learningcited by 9
  27. 2023pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharingcited by 9
  28. 2024Decentralized Directed Collaboration for Personalized Federated Learningcited by 9
  29. 2022On the effectiveness of partial variance reduction in federated learning with heterogeneous datacited by 8
  30. 2023FedHB: Hierarchical Bayesian Federated Learningcited by 8
  31. 2023Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Trainingcited by 8
  32. 2023HyperFed: Hyperbolic Prototypes Exploration with Consistent Aggregation for Non-IID Data in Federated Learningcited by 8
  33. 2023Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networkscited by 8
  34. 2024Spectral Co-Distillation for Personalized Federated Learningcited by 8
  35. 2024FedUV: Uniformity and Variance for Heterogeneous Federated Learningcited by 8
  36. 2024A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applicationscited by 8
  37. 2024Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Driftcited by 8
  38. 2025FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learningcited by 8

50 most cited of 180 All 180 (JSON)