Domain-Skewed Federated Learning with Feature Decoupling and Calibration

• URL: http://arxiv.org/abs/2603.14238v1
• Date: Sun, 15 Mar 2026 06:20:22 GMT
• Title: Domain-Skewed Federated Learning with Feature Decoupling and Calibration
• Abstract summary: Federated learning (FL) allows distributed clients to collaboratively train a global model in a privacy-preserving manner.<n>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.<n>We propose Federated Feature Decoupling andrimi ($F2$DC), which liberates valuable class-relevant information by calibrating the domain-specific biased features.
• Score: 35.05951359908686
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 ($F^2$DC), 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 $F^2$DC 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 $F^2$DC and the contributions of its two modules. Code is available at https://github.com/mala-lab/F2DC.

Related papers

• FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift [39.879063438848576]
  Federated Learning (FL) enables decentralized model training across multiple clients without exposing private data.<n>In real-world FL scenarios, clients often hold data from distinct domains, leading to severe domain shift and degraded global model performance.<n>We propose Federated Domain-Aware Prototypes (FedDAP) to construct domain-specific global prototypes.
  arXiv  Detail & Related papers  (2026-04-08T08:08:33Z)
• Adversarial Alignment and Disentanglement for Cross-Domain CTR Prediction with Domain-Encompassing Features [9.70128576544644]
  Cross-domain recommendation (CDR) has been increasingly explored to address data sparsity and cold-start issues.<n>Recent approaches typically disentangle domain-invariant features shared between source and target domains, as well as domain-specific features for each domain.<n>This paper presents the Adversarial Alignment and Disentanglement Cross-Domain Recommendation model, an innovative approach designed to capture a comprehensive range of cross-domain information.
  arXiv  Detail & Related papers  (2026-01-24T14:20:16Z)
• FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment [2.4472081831862655]
  Federated Learning (FL) offers a decentralized paradigm for collaborative model training without direct data sharing.<n>It poses unique challenges for Domain Generalization (DG), including strict privacy constraints, non-i.i.d. local data, and limited domain diversity.<n>We introduce FedAlign, a lightweight, privacy-preserving framework designed to enhance DG in federated settings.
  arXiv  Detail & Related papers  (2025-01-26T11:17:32Z)
• Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes [34.396534936178924]
  We introduce a novel federated prototype learning method, I$2$PFL, which incorporates $textbfI$ntra-domain and $textbfI$nter-domain.<n>We propose feature alignment with MixUp-based augmented prototypes to capture the diversity within local domains and enhance the generalization of local features.
  arXiv  Detail & Related papers  (2025-01-15T02:17:38Z)
• DomCLP: Domain-wise Contrastive Learning with Prototype Mixup for Unsupervised Domain Generalization [10.343546104340962]
  Self-supervised learning (SSL) methods based on the instance discrimination tasks with InfoNCE have achieved remarkable success.<n>UDG approaches utilize contrastive learning with InfoNCE to generate representations.<n>We propose DomCLP, Domain-wise Contrastive Learning with Prototype Mixup.
  arXiv  Detail & Related papers  (2024-12-12T08:59:08Z)
• Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting [67.38137379297717]
  Multidomain crowd counting aims to learn a general model for multiple diverse datasets. Deep networks prefer modeling distributions of the dominant domains instead of all domains, which is known as domain bias. We propose a Modulating Domain-specific Knowledge Network (MDKNet) to handle the domain bias issue in multidomain crowd counting.
  arXiv  Detail & Related papers  (2024-02-06T06:49:04Z)
• Dynamic Instance Domain Adaptation [109.53575039217094]
  Most studies on unsupervised domain adaptation assume that each domain's training samples come with domain labels. We develop a dynamic neural network with adaptive convolutional kernels to generate instance-adaptive residuals to adapt domain-agnostic deep features to each individual instance. Our model, dubbed DIDA-Net, achieves state-of-the-art performance on several commonly used single-source and multi-source UDA datasets.
  arXiv  Detail & Related papers  (2022-03-09T20:05:54Z)
• Federated and Generalized Person Re-identification through Domain and Feature Hallucinating [88.77196261300699]
  We study the problem of federated domain generalization (FedDG) for person re-identification (re-ID) We propose a novel method, called "Domain and Feature Hallucinating (DFH)", to produce diverse features for learning generalized local and global models. Our method achieves the state-of-the-art performance for FedDG on four large-scale re-ID benchmarks.
  arXiv  Detail & Related papers  (2022-03-05T09:15:13Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Disentanglement-based Cross-Domain Feature Augmentation for Effective Unsupervised Domain Adaptive Person Re-identification [87.72851934197936]
  Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching. One challenge is how to generate target domain samples with reliable labels for training. We propose a Disentanglement-based Cross-Domain Feature Augmentation strategy.
  arXiv  Detail & Related papers  (2021-03-25T15:28:41Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.