mlsanityData to 14 Oct 2026

Federated Out-of-Distribution Generalization: A Causal Augmentation View

arXiv 2504.19882 ↗First posted 28 Apr 2025cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Federated learning aims to collaboratively model by integrating multi-source information to obtain a model that can generalize across all client data. Existing methods often leverage knowledge distillation or data augmentation to mitigate the negative impact of data bias across clients. However, the limited performance of teacher models on out-of-distribution samples and the inherent quality gap between augmented and original data hinder their effectiveness and they typically fail to leverage the advantages of incorporating rich contextual information. To address these limitations, this paper proposes a Federated Causal Augmentation method, termed FedCAug, which employs causality-inspired data augmentation to break the spurious correlation between attributes and categories. Specifically, it designs a causal region localization module to accurately identify and decouple the background and objects in the image, providing rich contextual information for causal data augmentation. Additionally, it designs a causality-inspired data augmentation module that integrates causal features and within-client context to generate counterfactual samples. This significantly enhances data diversity, and the entire process does not require any information sharing between clients, thereby contributing to the protection of data privacy. Extensive experiments conducted on three datasets reveal that FedCAug markedly reduces the model's reliance on background to predict sample labels, achieving superior performance compared to state-of-the-art methods.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 58 references that are in the map. First posted on arXiv 28 Apr 2025.

Builds on

29 of 58 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  5. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  7. 2021Model-Contrastive Federated Learningcited by 766
  8. 2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 287
  9. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 212
  10. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  11. 2023FedGH: Heterogeneous Federated Learning with Generalized Global Headercited by 56
  12. 2022A Survey on Heterogeneous Federated Learningcited by 42
17 more
  1. 2022Federated Domain Generalization for Image Recognition via Cross-Client Style Transfercited by 40
  2. 2024Plug-in Diffusion Model for Sequential Recommendationcited by 37
  3. 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
  4. 2023Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Datacited by 35
  5. 2024Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversitycited by 30
  6. 2022Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferringcited by 28
  7. 2023StableFDG: Style and Attention Based Learning for Federated Domain Generalizationcited by 21
  8. 2024Federated Model Heterogeneous Matryoshka Representation Learningcited by 21
  9. 2023Triple Sequence Learning for Cross-domain Recommendationcited by 19
  10. 2022Meta-Causal Feature Learning for Out-of-Distribution Generalizationcited by 14
  11. 2024Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalizationcited by 12
  12. 2023FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learningcited by 10
  13. 2024Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalizationcited by 10
  14. 2023pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharingcited by 9
  15. 2023Cross-Modal Content Inference and Feature Enrichment for Cold-Start Recommendationcited by 5
  16. 2024Federated Cross-Training Learners for Robust Generalization under Data Heterogeneitycited by 1
  17. 2024Robust Visual Tracking via Iterative Gradient Descent and Threshold Selectioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalizationcited by 4
  2. 2025Geometric Prior-Guided Federated Prompt Calibrationcited by 2
  3. 2026Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification under Federated Domain Generalization with Causality-Inspired Interventionscited by 1
  4. 2025FedSDWC: Federated Synergistic Dual-Representation Weak Causal Learning for OODcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Towards Causal Federated Learning For Enhanced Robustness and Privacy
  2. 2025Global Intervention and Distillation for Federated Out-of-Distribution Generalization
  3. 2024Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data
  4. 2026FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning
  5. 2025Unlearning Clients, Features and Samples in Vertical Federated Learning
  6. 2026A Survey on Federated Causal Discovery and Inference
  7. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
  8. 2023Federated Learning with Diffusion Models for Privacy-Sensitive Vision Tasks