# Federated Learning with Domain Shift Eraser

arXiv: https://arxiv.org/abs/2503.13063 · HTML: https://mlsanity.com/paper/2503.13063/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 50 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 30 of 33)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [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)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://mlsanity.com/paper/2102.07623/) (2021)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Think Locally, Act Globally: Federated Learning with Local and Global Representations](https://mlsanity.com/paper/2001.01523/) (2020)
- [FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space](https://mlsanity.com/paper/2103.06030/) (2021)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [Personalized Federated Learning using Hypernetworks](https://mlsanity.com/paper/2103.04628/) (2021)
- [FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare](https://mlsanity.com/paper/1907.09173/) (2019)
- [FedBABU: Towards Enhanced Representation for Federated Image Classification](https://mlsanity.com/paper/2106.06042/) (2021)
- [Generalized Federated Learning via Sharpness Aware Minimization](https://mlsanity.com/paper/2206.02618/) (2022)
- [Federated Adversarial Domain Adaptation](https://mlsanity.com/paper/1911.02054/) (2019)
- [Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2111.14213/) (2021)
- [Layer-wised Model Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2205.03993/) (2022)
- [HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images](https://mlsanity.com/paper/2112.10775/) (2021)
- [Federated Learning with Fair Averaging](https://mlsanity.com/paper/2104.14937/) (2021)
- [Federated Learning Meets Multi-objective Optimization](https://mlsanity.com/paper/2006.11489/) (2020)
- [Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning](https://mlsanity.com/paper/2110.08394/) (2021)
- [FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data](https://mlsanity.com/paper/2211.09299/) (2022)
- [FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy](https://mlsanity.com/paper/2302.10429/) (2023)
- [Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity](https://mlsanity.com/paper/2405.16585/) (2024)

## Built on by (most cited first, 7 of 7)

- [Fractional-Order Federated Learning](https://mlsanity.com/paper/2602.15380/) (2026)
- [Domain-Skewed Federated Learning with Feature Decoupling and Calibration](https://mlsanity.com/paper/2603.14238/) (2026)
- [FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift](https://mlsanity.com/paper/2604.06795/) (2026)
- [HARMONY: Bridging the Personalization-Generalization Gap by Mitigating Representation Skew in Heterogeneous Split Federated Learning](https://mlsanity.com/paper/2605.07211/) (2026)
- [BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation](https://mlsanity.com/paper/2605.17508/) (2026)
- [Out-of-Distribution Federated Distillation with Domain-Aware Proxy](https://mlsanity.com/paper/2608.08525/) (2026)
- [When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation](https://mlsanity.com/paper/2608.15639/) (2026)

## Abstract (arXiv)

Federated learning (FL) is emerging as a promising technique for collaborative learning without local data leaving their devices. However, clients' data originating from diverse domains may degrade model performance due to domain shifts, preventing the model from learning consistent representation space. In this paper, we propose a novel FL framework, Federated Domain Shift Eraser (FDSE), to improve model performance by differently erasing each client's domain skew and enhancing their consensus. First, we formulate the model forward passing as an iterative deskewing process that extracts and then deskews features alternatively. This is efficiently achieved by decomposing each original layer in the neural network into a Domain-agnostic Feature Extractor (DFE) and a Domain-specific Skew Eraser (DSE). Then, a regularization term is applied to promise the effectiveness of feature deskewing by pulling local statistics of DSE's outputs close to the globally consistent ones. Finally, DFE modules are fairly aggregated and broadcast to all the clients to maximize their consensus, and DSE modules are personalized for each client via similarity-aware aggregation to erase their domain skew differently. Comprehensive experiments were conducted on three datasets to confirm the advantages of our method in terms of accuracy, efficiency, and generalizability.