Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) is increasingly adopted in domains like healthcare, where data privacy is paramount. A fundamental challenge in these systems is statistical heterogeneity-the fact that data distributions vary significantly across clients (e.g., different hospitals may treat distinct patient demographics). While current FL algorithms focus on aggregating model updates from these heterogeneous clients, the potential of the central server remains under-explored. This paper is motivated by a healthcare scenario: could a central server not only coordinate model training but also guide a new patient to the hospital best equipped for their specific condition? We generalize this idea to propose a novel paradigm for FL systems where the server actively guides the allocation of new tasks or queries to the most appropriate client. To enable this, we introduce a density ratio model and empirical likelihood-based framework that simultaneously addresses two goals: (1) learning effective local models on each client, and (2) finding the best matching client for a new query. Empirical results demonstrate the framework's effectiveness on benchmark datasets, showing improvements in both model accuracy and the precision of client guidance compared to standard FL approaches. This work opens a new direction for building more intelligent and resource-efficient FL systems that leverage heterogeneity as a feature, not just a bug. Code is available at https://github.com/zijianwang0510/FedDRM.git.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 55 references that are in the map. First posted on arXiv 27 Sep 2025.
Builds on
32 of 55 references.
References · 32
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
- 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
- 2021Model-Contrastive Federated Learningcited by 766
- 2017Federated Multi-Task Learningcited by 672
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2020Personalized Federated Learning with Moreau Envelopescited by 618
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2021Federated Learning Based on Dynamic Regularizationcited by 562
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
20 more
- 2020An Efficient Framework for Clustered Federated Learningcited by 511
- 2021Towards Personalized Federated Learningcited by 464
- 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
- 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
- 2019REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographscited by 228
- 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
- 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 182
- 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
- 2022Generalized Federated Learning via Sharpness Aware Minimizationcited by 144
- 2021Federated Learning for Open Bankingcited by 141
- 2022FedALA: Adaptive Local Aggregation for Personalized Federated Learningcited by 122
- 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 113
- 2023Personalized Federated Learning with Feature Alignment and Classifier Collaborationcited by 97
- 2022Layer-wised Model Aggregation for Personalized Federated Learningcited by 96
- 2023Personalized Federated Learning under Mixture of Distributionscited by 37
- 2022FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reductioncited by 35
- 2020Dynamic Clustering in Federated Learningcited by 27
- 2023Federated Learning with Extremely Noisy Clients via Negative Distillationcited by 12
- 2023Federated Learning on Virtual Heterogeneous Data with Local-global Distillationcited by 6
- 2024Positive and Unlabeled Data: Model, Estimation, Inference, and Classificationcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.