A systematic review of federated learning from clients' perspective: challenges and solutions

Y Shanmugarasa, H Paik, SS Kanhere… - Artificial Intelligence …, 2023 - Springer
Federated learning (FL) is a machine learning approach that decentralizes data and its
processing by allowing clients to train intermediate models on their devices with locally …

Addressing Skewed Heterogeneity via Federated Prototype Rectification With Personalization

S Guo, H Wang, S Lin, Z Kou… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Federated learning (FL) is an efficient framework designed to facilitate collaborative model
training across multiple distributed devices while preserving user data privacy. A significant …

A survey on class imbalance in federated learning

J Zhang, C Li, J Qi, J He - arXiv preprint arXiv:2303.11673, 2023 - arxiv.org
Federated learning, which allows multiple client devices in a network to jointly train a
machine learning model without direct exposure of clients' data, is an emerging distributed …

FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data

Z Xiao, Z Chen, L Liu, Y Feng, J Wu, W Liu… - arXiv preprint arXiv …, 2024 - arxiv.org
Federated Long-Tailed Learning (Fed-LT), a paradigm wherein data collected from
decentralized local clients manifests a globally prevalent long-tailed distribution, has …

Federated learning with ℓ1 regularization

Y Shi, Y Zhang, P Zhang, Y Xiao, L Niu - Pattern Recognition Letters, 2023 - Elsevier
Federated Learning (FL) is a widely adopted deep learning method that does not require the
collection of raw training data and solves specific learning tasks by federating distributed …

Dynamic heterogeneous federated learning with multi-level prototypes

S Guo, H Wang, X Geng - Pattern Recognition, 2024 - Elsevier
Federated learning shows promise as a privacy-preserving collaborative learning technique.
Existing research mainly focuses on skewing the class distribution across clients. However …

Federated learning with complete service commitment of data heterogeneity

Y Zhou, J Wang, Y Qin, X Kong, X Xie, H Qi… - Knowledge-Based …, 2025 - Elsevier
Federated Learning (FL) systems grapple with data statistical heterogeneity, primarily
manifested as non-iid label distribution skew and quantity skew. Label skew refers to the …

Inferring Class-Label Distribution in Federated Learning

R Ramakrishna, G Dán - Proceedings of the 15th ACM Workshop on …, 2022 - dl.acm.org
Federated Learning (FL) has become a popular distributed learning method for training
classifiers by using data that are private to individual clients. The clients´ data are typically …

WBSP: Addressing stragglers in distributed machine learning with worker-busy synchronous parallel

D Yang, B Hu, A Liu, AL Jin, KL Yeung, Y You - Parallel Computing, 2024 - Elsevier
Parameter server is widely used in distributed machine learning to accelerate training.
However, the increasing heterogeneity of workers' computing capabilities leads to the issue …

Federated deep long-tailed learning: A survey

K Li, Y Li, J Zhang, X Liu, Z Ma - Neurocomputing, 2024 - Elsevier
The federated learning privacy-preserving framework has achieved fruitful results in training
deep models across clients. This survey aims to provide a systematic overview of federated …