A systematic review of federated learning: Challenges, aggregation methods, and development tools
BS Guendouzi, S Ouchani, HEL Assaad… - Journal of Network and …, 2023 - Elsevier
Since its inception in 2016, federated learning has evolved into a highly promising decentral-
ized machine learning approach, facilitating collaborative model training across numerous …
ized machine learning approach, facilitating collaborative model training across numerous …
Federated domain generalization with generalization adjustment
Abstract Federated Domain Generalization (FedDG) attempts to learn a global model in a
privacy-preserving manner that generalizes well to new clients possibly with domain shift …
privacy-preserving manner that generalizes well to new clients possibly with domain shift …
Feddisco: Federated learning with discrepancy-aware collaboration
This work considers the category distribution heterogeneity in federated learning. This issue
is due to biased labeling preferences at multiple clients and is a typical setting of data …
is due to biased labeling preferences at multiple clients and is a typical setting of data …
Personalized federated learning with inferred collaboration graphs
Personalized federated learning (FL) aims to collaboratively train a personalized model for
each client. Previous methods do not adaptively determine who to collaborate at a fine …
each client. Previous methods do not adaptively determine who to collaborate at a fine …
No fear of classifier biases: Neural collapse inspired federated learning with synthetic and fixed classifier
Data heterogeneity is an inherent challenge that hinders the performance of federated
learning (FL). Recent studies have identified the biased classifiers of local models as the key …
learning (FL). Recent studies have identified the biased classifiers of local models as the key …
Non-iid data in federated learning: A systematic review with taxonomy, metrics, methods, frameworks and future directions
Recent advances in machine learning have highlighted Federated Learning (FL) as a
promising approach that enables multiple distributed users (so-called clients) to collectively …
promising approach that enables multiple distributed users (so-called clients) to collectively …
Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment
No-reference point cloud quality assessment (NR-PCQA) aims to automatically evaluate the
perceptual quality of distorted point clouds without available reference which have achieved …
perceptual quality of distorted point clouds without available reference which have achieved …
On harmonizing implicit subpopulations
Machine learning algorithms learned from data with skewed distributions usually suffer from
poor generalization, especially when minority classes matter as much as, or even more than …
poor generalization, especially when minority classes matter as much as, or even more than …
Adaptive model pruning and personalization for federated learning over wireless networks
Federated learning (FL) enables distributed learning across edge devices while protecting
data privacy. However, the learning accuracy decreases due to the heterogeneity of devices' …
data privacy. However, the learning accuracy decreases due to the heterogeneity of devices' …
Personalised federated learning on heterogeneous feature spaces
A Rakotomamonjy, M Vono, HJM Ruiz… - arxiv preprint arxiv …, 2023 - arxiv.org
Most personalised federated learning (FL) approaches assume that raw data of all clients
are defined in a common subspace ie all clients store their data according to the same …
are defined in a common subspace ie all clients store their data according to the same …