FedGCA: Global Consistent Augmentation Based Single-Source Federated Domain Generalization
Not on the map. Why?
Abstract (arXiv)
Federated Domain Generalization (FedDG) aims to train the global model for generalization ability to unseen domains with multi-domain training samples. However, clients in federated learning networks are often confined to a single, non-IID domain due to inherent sampling and temporal limitations. The lack of cross-domain interaction and the in-domain divergence impede the learning of domain-common features and limit the effectiveness of existing FedDG, referred to as the single-source FedDG (sFedDG) problem. To address this, we introduce the Federated Global Consistent Augmentation (FedGCA) method, which incorporates a style-complement module to augment data samples with diverse domain styles. To ensure the effective integration of augmented samples, FedGCA employs both global guided semantic consistency and class consistency, mitigating inconsistencies from local semantics within individual clients and classes across multiple clients. The conducted extensive experiments demonstrate the superiority of FedGCA.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 23 Sep 2024.
Builds on
16 of 21 references.
References · 16
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Deeper, Broader and Artier Domain Generalizationcited by 983
- 2021Model-Contrastive Federated Learningcited by 762
- 2021Federated Learning Based on Dynamic Regularizationcited by 555
- 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
- 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
- 2021Learning to Diversify for Single Domain Generalizationcited by 170
- 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
- 2020Robust and Generalizable Visual Representation Learning via Random Convolutionscited by 141
- 2020Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustnesscited by 121
- 2021Residual Attention: A Simple but Effective Method for Multi-Label Recognitioncited by 52
- 2021Federated Learning with Domain Generalizationcited by 41
4 more
- 2022Attention Consistency on Visual Corruptions for Single-Source Domain Generalizationcited by 37
- 2023Progressive Random Convolutions for Single Domain Generalizationcited by 33
- 2021Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approachcited by 18
- 2022On the Convergence of Multi-Server Federated Learning with Overlapping Areacited by 8
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.