# Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains

arXiv: https://arxiv.org/abs/2403.09048 · HTML: https://mlsanity.com/paper/2403.09048/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [Federated Learning from Pre-Trained Models: A Contrastive Learning Approach](https://mlsanity.com/paper/2209.10083/) (2022)
- [The Discrete Gaussian for Differential Privacy](https://mlsanity.com/paper/2004.00010/) (2020)
- [Overcoming Forgetting in Federated Learning on Non-IID Data](https://mlsanity.com/paper/1910.07796/) (2019)
- [Efficient Parameter-free Clustering Using First Neighbor Relations](https://mlsanity.com/paper/1902.11266/) (2019)
- [Federated Unsupervised Representation Learning](https://mlsanity.com/paper/2010.08982/) (2020)
- [FedProc: Prototypical Contrastive Federated Learning on Non-IID data](https://mlsanity.com/paper/2109.12273/) (2021)
- [Tackling Data Heterogeneity in Federated Learning with Class Prototypes](https://mlsanity.com/paper/2212.02758/) (2022)
- [FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning](https://mlsanity.com/paper/2207.14130/) (2022)
- [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021)
- [FedCorr: Multi-Stage Federated Learning for Label Noise Correction](https://mlsanity.com/paper/2204.04677/) (2022)
- [Federated Learning with Domain Generalization](https://mlsanity.com/paper/2111.10487/) (2021)
- [Robust Federated Learning with Noisy Labels](https://mlsanity.com/paper/2012.01700/) (2020)

## Built on by (most cited first, 28 of 28)

- [LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement](https://mlsanity.com/paper/2411.14961/) (2024)
- [FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging](https://mlsanity.com/paper/2507.20016/) (2025)
- [FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models](https://mlsanity.com/paper/2510.27486/) (2025)
- [FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRA](https://mlsanity.com/paper/2503.11880/) (2025)
- [Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning](https://mlsanity.com/paper/2509.15087/) (2025)
- [Prioritizing Modalities: Flexible Importance Scheduling in Federated Multimodal Learning](https://mlsanity.com/paper/2408.06549/) (2024)
- [FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2510.20250/) (2025)
- [FedEL: Federated Elastic Learning for Heterogeneous Devices](https://mlsanity.com/paper/2509.16902/) (2025)
- [Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation](https://mlsanity.com/paper/2511.10945/) (2025)
- [Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning](https://mlsanity.com/paper/2503.13543/) (2025)
- [FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift](https://mlsanity.com/paper/2507.04781/) (2025)
- [C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning](https://mlsanity.com/paper/2509.19674/) (2025)
- [FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning](https://mlsanity.com/paper/2603.13282/) (2026)
- [Modality Alignment Meets Federated Broadcasting](https://mlsanity.com/paper/2411.15837/) (2024)
- [Mitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes](https://mlsanity.com/paper/2501.08521/) (2025)
- [FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypes](https://mlsanity.com/paper/2502.16119/) (2025)
- [FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning](https://mlsanity.com/paper/2511.22265/) (2025)
- [An Enhanced Federated Prototype Learning Method under Domain Shift](https://mlsanity.com/paper/2409.18578/) (2024)
- [FEDEXCHANGE: Bridging the Domain Gap in Federated Object Detection for Free](https://mlsanity.com/paper/2509.10503/) (2025)
- [BAPFL: Exploring Backdoor Attacks Against Prototype-based Federated Learning](https://mlsanity.com/paper/2509.12964/) (2025)
- [A Multi-Prototype-Guided Federated Knowledge Distillation Approach in AI-RAN Enabled Multi-Access Edge Computing System](https://mlsanity.com/paper/2603.09727/) (2026)
- [Computation and Communication Efficient Federated Unlearning via On-server Gradient Conflict Mitigation and Expression](https://mlsanity.com/paper/2603.13795/) (2026)
- [FedDAP: Domain-Aware Prototype Learning for Federated Learning under Domain Shift](https://mlsanity.com/paper/2604.06795/) (2026)
- [From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning](https://mlsanity.com/paper/2605.05959/) (2026)
- [FedProIn: Mitigating Client Drift for Learnable Prototypes in Federated Medical Imaging](https://mlsanity.com/paper/2607.04158/) (2026)
- [FedCausal-Dyn: A Causal-Dynamic Paradigm for Federated Learning under Dynamic Feature Drift](https://mlsanity.com/paper/2607.09695/) (2026)
- [When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation](https://mlsanity.com/paper/2608.15639/) (2026)
- [Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentation](https://mlsanity.com/paper/2610.04700/) (2026)

## Abstract (arXiv)

Federated learning (FL) allows collaborative machine learning training without sharing private data. While most FL methods assume identical data domains across clients, real-world scenarios often involve heterogeneous data domains. Federated Prototype Learning (FedPL) addresses this issue, using mean feature vectors as prototypes to enhance model generalization. However, existing FedPL methods create the same number of prototypes for each client, leading to cross-domain performance gaps and disparities for clients with varied data distributions. To mitigate cross-domain feature representation variance, we introduce FedPLVM, which establishes variance-aware dual-level prototypes clustering and employs a novel α-sparsity prototype loss. The dual-level prototypes clustering strategy creates local clustered prototypes based on private data features, then performs global prototypes clustering to reduce communication complexity and preserve local data privacy. The α-sparsity prototype loss aligns samples from underrepresented domains, enhancing intra-class similarity and reducing inter-class similarity. Evaluations on Digit-5, Office-10, and DomainNet datasets demonstrate our method's superiority over existing approaches.