mlsanityData to 14 Oct 2026

StableFDG: Style and Attention Based Learning for Federated Domain Generalization

arXiv 2311.00227 ↗First posted 1 Nov 2023cs.LG cs.AIcited by 21

Not on the map. Why?

Abstract (arXiv)

Traditional federated learning (FL) algorithms operate under the assumption that the data distributions at training (source domains) and testing (target domain) are the same. The fact that domain shifts often occur in practice necessitates equipping FL methods with a domain generalization (DG) capability. However, existing DG algorithms face fundamental challenges in FL setups due to the lack of samples/domains in each client's local dataset. In this paper, we propose StableFDG, a style and attention based learning strategy for accomplishing federated domain generalization, introducing two key contributions. The first is style-based learning, which enables each client to explore novel styles beyond the original source domains in its local dataset, improving domain diversity based on the proposed style sharing, shifting, and exploration strategies. Our second contribution is an attention-based feature highlighter, which captures the similarities between the features of data samples in the same class, and emphasizes the important/common characteristics to better learn the domain-invariant characteristics of each class in data-poor FL scenarios. Experimental results show that StableFDG outperforms existing baselines on various DG benchmark datasets, demonstrating its efficacy.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 28 of its 39 references that are in the map. First posted on arXiv 1 Nov 2023.

Builds on

28 of 39 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  7. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  9. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  10. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  11. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  12. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
16 more
  1. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  2. 2021Domain Generalization with MixStylecited by 566
  3. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  4. 2019Attention Augmented Convolutional Networkscited by 363
  5. 2020Adaptive Personalized Federated Learningcited by 358
  6. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  7. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  8. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  9. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  10. 2019Episodic Training for Domain Generalizationcited by 245
  11. 2018Domain Generalization via Conditional Invariant Representationcited by 146
  12. 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 125
  13. 2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
  14. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  15. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  16. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 7; 2025: 13.

21 papers.

Sort:

By area:

  1. 2024DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devicescited by 9
  2. 2024Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradientscited by 7
  3. 2025Federated Domain Generalization with Data-free On-server Matching Gradientcited by 7
  4. 2025FedAlign: Federated Domain Generalization with Cross-Client Feature Alignmentcited by 5
  5. 2025Selective Attention Federated Learning: Improving Privacy and Efficiency for Clinical Text Classificationcited by 5
  6. 2025Federated Out-of-Distribution Generalization: A Causal Augmentation Viewcited by 4
  7. 2025Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalizationcited by 4
  8. 2024Boosting Federated Domain Generalization: Understanding the Role of Advanced Pre-Trained Architecturescited by 3
  9. 2025Global Intervention and Distillation for Federated Out-of-Distribution Generalizationcited by 3
  10. 2024FedCCRL: Federated Domain Generalization with Cross-Client Representation Learningcited by 2
  11. 2024Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?cited by 2
  12. 2025FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysiscited by 2
9 more
  1. 2023Federated Active Learning for Target Domain Generalisationcited by 0
  2. 2024FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuningcited by 0
  3. 2024PARDON: Privacy-Aware and Robust Federated Domain Generalizationcited by 0
  4. 2025Decentralized Domain Generalization with Style Sharing: Formal Model and Convergence Analysiscited by 0
  5. 2025Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalizationcited by 0
  6. 2025Multi-Source Collaborative Style Augmentation and Domain-Invariant Learning for Federated Domain Generalizationcited by 0
  7. 2025Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domainscited by 0
  8. 2025TreeFedDG: Alleviating Global Drift in Federated Domain Generalization for Medical Image Segmentationcited by 0
  9. 2025Federated Domain Generalization with Latent Space Inversioncited by 0