mlsanityData to 14 Oct 2026

Domain-Skewed Federated Learning with Feature Decoupling and Calibration

arXiv 2603.14238 ↗First posted 15 Mar 2026cs.LG cs.MMcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) allows distributed clients to collaboratively train a global model in a privacy-preserving manner. However, one major challenge is domain skew, where clients' data originating from diverse domains may hinder the aggregated global model from learning a consistent representation space, resulting in poor generalizable ability in multiple domains. In this paper, we argue that the domain skew is reflected in the domain-specific biased features of each client, causing the local model's representations to collapse into a narrow low-dimensional subspace. We then propose Federated Feature Decoupling and Calibration (F2DC), which liberates valuable class-relevant information by calibrating the domain-specific biased features, enabling more consistent representations across domains. A novel component, Domain Feature Decoupler (DFD), is first introduced in F2DC to determine the robustness of each feature unit, thereby separating the local features into domain-robust features and domain-related features. A Domain Feature Corrector (DFC) is further proposed to calibrate these domain-related features by explicitly linking discriminative signals, capturing additional class-relevant clues that complement the domain-robust features. Finally, a domain-aware aggregation of the local models is performed to promote consensus among clients. Empirical results on three popular multi-domain datasets demonstrate the effectiveness of the proposed F2DC and the contributions of its two modules. Code is available at https://github.com/mala-lab/F2DC.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 57 references that are in the map. First posted on arXiv 15 Mar 2026.

Builds on

40 of 57 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  7. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  8. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  9. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  10. 2021Model-Contrastive Federated Learningcited by 766
  11. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  12. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 583
28 more
  1. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  2. 2020Understanding the Behaviour of Contrastive Losscited by 398
  3. 2019Fair Resource Allocation in Federated Learningcited by 394
  4. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  5. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  6. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 122
  7. 2022Disentangled Representation Learningcited by 112
  8. 2019Learning Disentangled Representations for Recommendationcited by 110
  9. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 99
  10. 2020Rethinking Differentiable Search for Mixed-Precision Neural Networkscited by 82
  11. 2019Gait Recognition via Disentangled Representation Learningcited by 70
  12. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 67
  13. 2021HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Imagescited by 64
  14. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
  15. 2024An Aggregation-Free Federated Learning for Tackling Data Heterogeneitycited by 33
  16. 2023Leveraging sparse and shared feature activations for disentangled representation learningcited by 32
  17. 2024Relaxed Contrastive Learning for Federated Learningcited by 32
  18. 2024DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learningcited by 32
  19. 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 30
  20. 2022DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graphcited by 21
  21. 2024Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matchingcited by 21
  22. 2024Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approachcited by 9
  23. 2025FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learningcited by 8
  24. 2025Federated Learning with Domain Shift Erasercited by 7
  25. 2025Federated Learning with Sample-level Client Drift Mitigationcited by 6
  26. 2025FedSC: Federated Learning with Semantic-Aware Collaborationcited by 3
  27. 2025FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learningcited by 3
  28. 2025FedSKC: Federated Learning with Non-IID Data via Structural Knowledge Collaborationcited by 1

Built on by

Not cited yet.