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 …

Federated domain generalization with generalization adjustment

R Zhang, Q Xu, J Yao, Y Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Feddisco: Federated learning with discrepancy-aware collaboration

R Ye, M Xu, J Wang, C Xu, S Chen… - … on Machine Learning, 2023 - proceedings.mlr.press
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 …

Personalized federated learning with inferred collaboration graphs

R Ye, Z Ni, F Wu, S Chen… - … Conference on Machine …, 2023 - proceedings.mlr.press
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 …

No fear of classifier biases: Neural collapse inspired federated learning with synthetic and fixed classifier

Z Li, X Shang, R He, T Lin… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
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 …

Non-iid data in federated learning: A systematic review with taxonomy, metrics, methods, frameworks and future directions

D Solans, M Heikkila, A Vitaletti, N Kourtellis… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent advances in machine learning have highlighted Federated Learning (FL) as a
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

Z Shan, Y Zhang, Q Yang, H Yang… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …

On harmonizing implicit subpopulations

F Hong, J Yao, Y Lyu, Z Zhou, I Tsang… - The Twelfth …, 2023 - openreview.net
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 …

Adaptive model pruning and personalization for federated learning over wireless networks

X Liu, T Ratnarajah, M Sellathurai… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Federated learning (FL) enables distributed learning across edge devices while protecting
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 …