A systematic review of federated learning from clients' perspective: challenges and solutions
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 …
processing by allowing clients to train intermediate models on their devices with locally …
Addressing Skewed Heterogeneity via Federated Prototype Rectification With Personalization
Federated learning (FL) is an efficient framework designed to facilitate collaborative model
training across multiple distributed devices while preserving user data privacy. A significant …
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 …
machine learning model without direct exposure of clients' data, is an emerging distributed …
FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
Federated Long-Tailed Learning (Fed-LT), a paradigm wherein data collected from
decentralized local clients manifests a globally prevalent long-tailed distribution, has …
decentralized local clients manifests a globally prevalent long-tailed distribution, has …
Federated learning with ℓ1 regularization
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 …
collection of raw training data and solves specific learning tasks by federating distributed …
Dynamic heterogeneous federated learning with multi-level prototypes
Federated learning shows promise as a privacy-preserving collaborative learning technique.
Existing research mainly focuses on skewing the class distribution across clients. However …
Existing research mainly focuses on skewing the class distribution across clients. However …
Federated learning with complete service commitment of data heterogeneity
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 …
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 …
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
Parameter server is widely used in distributed machine learning to accelerate training.
However, the increasing heterogeneity of workers' computing capabilities leads to the issue …
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 …
deep models across clients. This survey aims to provide a systematic overview of federated …