FedDAR: Federated Learning With Data-Quantity Aware Regularization for Heterogeneous Distributed Data

Federated learning (FL) has emerged as a promising approach for collaboratively training global models and classifiers without sharing private data. However, existing studies primarily focus on distinct methodologies for typical and personalized FL (tFL and pFL), representing a challenge in explorin...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 13; s. 133208 - 133217
Hlavní autoři: Kwak, Youngjun, Jung, Minyoung
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Adaptation models
augmentation
classification
communication efficiency
Computational modeling
Costs
Data models
data-quantity awareness
Distributed databases
Feature extraction
Federated learning
Machine learning
Predictive models
Regularization
Servers
Training
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Federated learning (FL) has emerged as a promising approach for collaboratively training global models and classifiers without sharing private data. However, existing studies primarily focus on distinct methodologies for typical and personalized FL (tFL and pFL), representing a challenge in exploring cross-applicable training methods. Moreover, previous approaches often rely on data and feature augmentation branches, overlooking data-quantity considerations, leading to suboptimal performance and inefficient communication costs, particularly in multi-class classification tasks. To address these challenges, we propose a novel add-on regularization technique for existing FL methods, named Data-quantity Aware Regularization (FedDAR), seamlessly integrating with existing tFL and pFL frameworks. This network-agnostic methodology reformulates the local training procedure by incorporating two crucial components: 1) enriched-feature augmentation, where features of the local model are coordinated with pre-initialized features to ensure unbiased-representations with efficient global communication rounds for unbalanced data distribution, and 2) data-quantity aware branch, which associates with local data size to improve the optimization of the local model using both supervised and self-supervised labels. We demonstrate significant performance improvements in tFL and pFL, achieving state-of-the-art results across MNIST, F-MNIST, CIFAR-10/100, and Tiny-ImageNet benchmarks.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2025.3591839