Cargando…
Fair detection of poisoning attacks in federated learning on non-i.i.d. data
Reconciling machine learning with individual privacy is one of the main motivations behind federated learning (FL), a decentralized machine learning technique that aggregates partial models trained by clients on their own private data to obtain a global deep learning model. Even if FL provides stron...
Autores principales: | Singh, Ashneet Khandpur, Blanco-Justicia, Alberto, Domingo-Ferrer, Josep |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer US
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9812008/ https://www.ncbi.nlm.nih.gov/pubmed/36619003 http://dx.doi.org/10.1007/s10618-022-00912-6 |
Ejemplares similares
-
An Optimization Method for Non-IID Federated Learning Based on Deep Reinforcement Learning
por: Meng, Xutao, et al.
Publicado: (2023) -
DAG-Based Blockchain Sharding for Secure Federated Learning with Non-IID Data
por: Lee, Jungjae, et al.
Publicado: (2022) -
Performance Enhancement in Federated Learning by Reducing Class Imbalance of Non-IID Data
por: Seol, Mihye, et al.
Publicado: (2023) -
Cross-Domain Federated Data Modeling on Non-IID Data
por: Chai, Baobao, et al.
Publicado: (2022) -
LoAdaBoost: Loss-based AdaBoost federated machine learning with reduced computational complexity on IID and non-IID intensive care data
por: Huang, Li, et al.
Publicado: (2020)