# Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization

arXiv: https://arxiv.org/abs/2505.04979 · HTML: https://mlsanity.com/paper/2505.04979/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 67 references that are in the map.
- First posted on arXiv 8 May 2025.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space](https://mlsanity.com/paper/2103.06030/) (2021)
- [FedProc: Prototypical Contrastive Federated Learning on Non-IID data](https://mlsanity.com/paper/2109.12273/) (2021)
- [Causal Attention for Unbiased Visual Recognition](https://mlsanity.com/paper/2108.08782/) (2021)
- [FedGH: Heterogeneous Federated Learning with Generalized Global Header](https://mlsanity.com/paper/2303.13137/) (2023)
- [FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data](https://mlsanity.com/paper/2211.09299/) (2022)
- [Federated Domain Generalization for Image Recognition via Cross-Client Style Transfer](https://mlsanity.com/paper/2210.00912/) (2022)
- [Advances and Open Challenges in Federated Foundation Models](https://mlsanity.com/paper/2404.15381/) (2024)
- [Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning](https://mlsanity.com/paper/2210.02326/) (2022)
- [Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2308.03457/) (2023)
- [Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity](https://mlsanity.com/paper/2405.16585/) (2024)
- [Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring](https://mlsanity.com/paper/2206.06818/) (2022)
- [DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2309.13546/) (2023)
- [FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation](https://mlsanity.com/paper/2310.00339/) (2023)
- [Mitigating Data Heterogeneity in Federated Learning with Data Augmentation](https://mlsanity.com/paper/2206.09979/) (2022)
- [StableFDG: Style and Attention Based Learning for Federated Domain Generalization](https://mlsanity.com/paper/2311.00227/) (2023)
- [Federated Model Heterogeneous Matryoshka Representation Learning](https://mlsanity.com/paper/2406.00488/) (2024)
- [Ten Challenging Problems in Federated Foundation Models](https://mlsanity.com/paper/2502.12176/) (2025)
- [Feature Distribution Matching for Federated Domain Generalization](https://mlsanity.com/paper/2203.11635/) (2022)
- [Multi-source Domain Adaptation for Visual Sentiment Classification](https://mlsanity.com/paper/2001.03886/) (2020)
- [Meta-Causal Feature Learning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2208.10156/) (2022)
- [FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection](https://mlsanity.com/paper/2410.11397/) (2024)
- [Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization](https://mlsanity.com/paper/2401.10272/) (2024)
- [GitFL: Adaptive Asynchronous Federated Learning using Version Control](https://mlsanity.com/paper/2211.12049/) (2022)

## Built on by (most cited first, 4 of 4)

- [Class-wise Balancing Data Replay for Federated Class-Incremental Learning](https://mlsanity.com/paper/2507.07712/) (2025)
- [Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning](https://mlsanity.com/paper/2509.22700/) (2025)
- [Federated Incomplete Multi-view Clustering with Globally Fused Graph Guidance](https://mlsanity.com/paper/2506.15703/) (2025)
- [Out-of-Distribution Federated Distillation with Domain-Aware Proxy](https://mlsanity.com/paper/2608.08525/) (2026)

## Abstract (arXiv)

Attribute bias in federated learning (FL) typically leads local models to optimize inconsistently due to the learning of non-causal associations, resulting degraded performance. Existing methods either use data augmentation for increasing sample diversity or knowledge distillation for learning invariant representations to address this problem. However, they lack a comprehensive analysis of the inference paths, and the interference from confounding factors limits their performance. To address these limitations, we propose the underlineFederated underlineDeconfounding and underlineDebiasing underlineLearning (FedDDL) method. It constructs a structured causal graph to analyze the model inference process, and performs backdoor adjustment to eliminate confounding paths. Specifically, we design an intra-client deconfounding learning module for computer vision tasks to decouple background and objects, generating counterfactual samples that establish a connection between the background and any label, which stops the model from using the background to infer the label. Moreover, we design an inter-client debiasing learning module to construct causal prototypes to reduce the proportion of the background in prototype components. Notably, it bridges the gap between heterogeneous representations via causal prototypical regularization. Extensive experiments on 2 benchmarking datasets demonstrate that methodname significantly enhances the model capability to focus on main objects in unseen data, leading to 4.5% higher Top-1 Accuracy on average over 9 state-of-the-art existing methods.