mlsanityData to 7 Oct 2026

FedSDAF: Leveraging Source Domain Awareness for Enhanced Federated Domain Generalization

arXiv 2505.02515 ↗First posted 5 May 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Traditional Federated Domain Generalization (FedDG) methods focus on learning domain-invariant features or adapting to unseen target domains, often overlooking the unique knowledge embedded within the source domain, especially in strictly isolated federated learning environments. Through experimentation, we discovered a counterintuitive phenomenon: features learned from a complete source domain have superior generalization capabilities compared to those learned directly from the target domain. This insight leads us to propose the Federated Source Domain Awareness Framework (FedSDAF), the first systematic approach to enhance FedDG by leveraging source domain-aware features. FedSDAF employs a dual-adapter architecture that decouples "local expertise" from "global generalization consensus." A Domain-Aware Adapter, retained locally, extracts and protects the unique discriminative knowledge of each source domain, while a Domain-Invariant Adapter, shared across clients, builds a robust global consensus. To enable knowledge exchange, we introduce a Bidirectional Knowledge Distillation mechanism that facilitates efficient dialogue between the adapters. Extensive experiments on four benchmark datasets (OfficeHome, PACS, VLCS, and DomainNet) show that FedSDAF significantly outperforms existing FedDG methods. The source code is available at https://github.com/pizzareapers/FedSDAF.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 59 references that are in the map. First posted on arXiv 5 May 2025.

Builds on

36 of 59 references.

References · 36

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  6. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  7. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  8. 2021Domain Generalization: A Surveycited by 760
  9. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  10. 2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
  11. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
  12. 2019Federated Adversarial Domain Adaptationcited by 140
24 more
  1. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
  2. 2022PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Modelcited by 133
  3. 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 121
  4. 2023FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learningcited by 70
  5. 2021What Do We Mean by Generalization in Federated Learning?cited by 62
  6. 2022Prompt Vision Transformer for Domain Generalizationcited by 52
  7. 2021Federated Learning with Domain Generalizationcited by 41
  8. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40
  9. 2023Learning Federated Visual Prompt in Null Space for MRI Reconstructioncited by 40
  10. 2022FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformerscited by 33
  11. 2022Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learningcited by 29
  12. 2024Rethinking Multi-domain Generalization with A General Learning Objectivecited by 23
  13. 2024FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Modelscited by 19
  14. 2024Single Domain Generalization for Crowd Countingcited by 17
  15. 2024FedClust: Optimizing Federated Learning on Non-IID Data through Weight-Driven Client Clusteringcited by 9
  16. 2023Aggregation of Disentanglement: Reconsidering Domain Variations in Domain Generalizationcited by 8
  17. 2024HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalizationcited by 8
  18. 2024DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detectioncited by 8
  19. 2024Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Modelscited by 6
  20. 2024Masked Random Noise for Communication Efficient Federated Learningcited by 4
  21. 2023A Two-Stage Framework with Self-Supervised Distillation For Cross-Domain Text Classificationcited by 3
  22. 2024FedGCA: Global Consistent Augmentation Based Single-Source Federated Domain Generalizationcited by 3
  23. 2024Communication-Efficient Federated Group Distributionally Robust Optimizationcited by 3
  24. 2024FedPartWhole: Federated domain generalization via consistent part-whole hierarchiescited by 1

Built on by

Not cited yet.