mlsanityData to 14 Oct 2026

FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation

arXiv 2512.06738 ↗First posted 7 Dec 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We address the Federated source-Free Domain Adaptation (FFreeDA) problem, with clients holding unlabeled data with significant inter-client domain gaps. The FFreeDA setup constrains the FL frameworks to employ only a pre-trained server model as the setup restricts access to the source dataset during the training rounds. Often, this source domain dataset has a distinct distribution to the clients' domains. To address the challenges posed by the FFreeDA setup, adaptation of the Source-Free Domain Adaptation (SFDA) methods to FL struggles with client-drift in real-world scenarios due to extreme data heterogeneity caused by the aforementioned domain gaps, resulting in unreliable pseudo-labels. In this paper, we introduce FedSCAl, an FL framework leveraging our proposed Server-Client Alignment (SCAl) mechanism to regularize client updates by aligning the clients' and server model's predictions. We observe an improvement in the clients' pseudo-labeling accuracy post alignment, as the SCAl mechanism helps to mitigate the client-drift. Further, we present extensive experiments on benchmark vision datasets showcasing how FedSCAl consistently outperforms state-of-the-art FL methods in the FFreeDA setup for classification tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 7 Dec 2025.

Builds on

31 of 53 references.

References · 31

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  4. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  5. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  6. 2021Model-Contrastive Federated Learningcited by 766
  7. 2020The Future of Digital Health with Federated Learningcited by 633
  8. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  9. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
  10. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  11. 2021Towards Personalized Federated Learningcited by 464
  12. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
19 more
  1. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  2. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  3. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  4. 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
  5. 2019Federated Adversarial Domain Adaptationcited by 140
  6. 2020Federated Visual Classification with Real-World Data Distributioncited by 128
  7. 2019Federated Learning for Emoji Prediction in a Mobile Keyboardcited by 118
  8. 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 113
  9. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
  10. 2020Distilled One-Shot Federated Learningcited by 109
  11. 2022Improving Generalization in Federated Learning by Seeking Flat Minimacited by 98
  12. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  13. 2023Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generationcited by 54
  14. 2023FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracycited by 49
  15. 2021SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Trainingcited by 45
  16. 2021Federated Multi-Target Domain Adaptationcited by 44
  17. 2022BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptationcited by 39
  18. 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
  19. 2024Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Datacited by 4

Built on by

Not cited yet.