Results 251 to 260 of about 1,993,316 (300)

Federated ConvNeXt-swin temporal fusion network for malware and botnet detection in IoT systems. [PDF]

Sci Rep
Alsubaei FS, Almazroi AA, Ayub N.
europepmc   +1 more source

A federated learning framework for deep imputation of missing data in heterogeneous ICU time series. [PDF]

Sci Rep
Vavekanand R, Sathio AA, Sultani M.
europepmc   +1 more source

Advanced behavioral malware detection: a comprehensive MLOps framework with federated learning and real-time drift detection. [PDF]

Front Artif Intell
El-Hajj M, Zeineddine MAJ.
europepmc   +1 more source

Dynamic variance-aware federated tuning for efficient autonomous vehicle perception under non-IID settings. [PDF]

Front Robot AI
Dhanavarshini V, Periyasamy S.
europepmc   +1 more source

Federated learning for heterogeneous electronic health record systems with cost effective participant selection. [PDF]

Sci Rep
Kim J, Kim J, Hur K, Choi E.
europepmc   +1 more source

Combining parameter fragmentation and group shuffling to defend against the untrustworthy server in federated learning. [PDF]

Sci Rep
Guo H, Chen W, Li J, Geng X.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

A review on client selection models in federated learning

Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2023
AbstractFederated learning (FL) is a decentralized machine learning (ML) technique that enables multiple clients to collaboratively train a common ML model without them having to share their raw data with each other. A typical FL process involves (1) FL client(s) selection, (2) global model distribution, (3) local training, and (4) aggregation. As such
Monalisa Panigrahi
exaly   +2 more sources

Client Selection for Federated Learning With Label Noise

IEEE Transactions on Vehicular Technology, 2022
Federated learning (FL) unleashes the full potential of training a global statistical model collaboratively from edge clients. In wireless FL, for the scarcity of spectrum, only a fraction of clients are capable to participate in the FL training in each round. On the other hand, the performance of FL suffers from the label noise, which naturally exists
Yong Zhou, Hua Qian, Miao Yang
exaly   +2 more sources