Personalized federated learning based on multi-head attention algorithm

Jiang, Shanshan; Lu, Meixia; Hu, Kai; Wu, Jiasheng; Li, Yaogen; Weng, Liguo; Xia, Min; Lin, Haifeng

doi:10.1007/s13042-023-01864-z

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Article3

Other1

Relationship

Self Cite0

Independent4

Authors

Journals

Cited by 4 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In traditional FL, a central server aggregates model parameter and distributes the global model, posing a single point of failure susceptible to attacks or crashes [6]. Blockchain integration addresses this limitation by decentralizing the coordination process, replacing the need for a central server.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Federated Learning Security, Scalability, and Future Incentives

2024

Adv Mach Lear Art Inte

View full text Add to dashboard Cite

This study delves into the integration of Storj and blockchain technology within the context of federated learning (FL) and its implications for scalability and efficiency. By leveraging blockchain, we aimed to bolster security and transparency, while also addressing storage challenges through the integration of Incremental Learning. Our findings revealed that while the utilization of Storj led to marginally higher federated server storage requirements compared to local storage, particularly as the number of clients increased, there was also a slight increase in the time required for the federated learning process when Storj was integrated, especially with a larger number of clients.

show abstract

Section: Introductionmentioning

confidence: 99%