mlsanityData to 14 Oct 2026

Federated Learning with Domain Shift Eraser

arXiv 2503.13063 ↗First posted 17 Mar 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) is emerging as a promising technique for collaborative learning without local data leaving their devices. However, clients' data originating from diverse domains may degrade model performance due to domain shifts, preventing the model from learning consistent representation space. In this paper, we propose a novel FL framework, Federated Domain Shift Eraser (FDSE), to improve model performance by differently erasing each client's domain skew and enhancing their consensus. First, we formulate the model forward passing as an iterative deskewing process that extracts and then deskews features alternatively. This is efficiently achieved by decomposing each original layer in the neural network into a Domain-agnostic Feature Extractor (DFE) and a Domain-specific Skew Eraser (DSE). Then, a regularization term is applied to promise the effectiveness of feature deskewing by pulling local statistics of DSE's outputs close to the globally consistent ones. Finally, DFE modules are fairly aggregated and broadcast to all the clients to maximize their consensus, and DSE modules are personalized for each client via similarity-aware aggregation to erase their domain skew differently. Comprehensive experiments were conducted on three datasets to confirm the advantages of our method in terms of accuracy, efficiency, and generalizability.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

33 of 50 references.

References · 33

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  6. 2018Federated Learning with Non-IID Datacited by 1,108
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  8. 2021Model-Contrastive Federated Learningcited by 766
  9. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  10. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  11. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  12. 2019GhostNet: More Features from Cheap Operationscited by 410
21 more
  1. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  2. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  3. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  4. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  5. 2021Personalized Federated Learning using Hypernetworkscited by 212
  6. 2019FedHealth: A Federated Transfer Learning Framework for Wearable Healthcarecited by 182
  7. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
  8. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  9. 2019Federated Adversarial Domain Adaptationcited by 140
  10. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  11. 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 96
  12. 2021HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Imagescited by 64
  13. 2021Federated Learning with Fair Averagingcited by 61
  14. 2020Federated Learning Meets Multi-objective Optimizationcited by 53
  15. 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
  16. 2022FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Datacited by 50
  17. 2023FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracycited by 49
  18. 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 30
  19. 2022FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providerscited by 14
  20. 2023FLGo: A Fully Customizable Federated Learning Platformcited by 12
  21. 2024Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Cloudscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Fractional-Order Federated Learningcited by 0
  2. 2026Domain-Skewed Federated Learning with Feature Decoupling and Calibrationcited by 0
  3. 2026FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shiftcited by 0
  4. 2026HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learningcited by 0
  5. 2026BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregationcited by 0
  6. 2026Out-of-Distribution Federated Distillation with Domain-Aware Proxycited by 0
  7. 2026When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimationcited by 0