Enhancing the blockchain interoperability through federated learning with directed acyclic graph
Abstract The use of federated learning to achieve blockchain interoperability has become a hot topic in research, because it enables data exchange without revealing any private information. However, the previous work, such as ScaleSFL (Asia‐CCS, 2022), that has implemented federated learning for blo...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-12-01
|
Series: | IET Blockchain |
Subjects: | |
Online Access: | https://doi.org/10.1049/blc2.12033 |
_version_ | 1797435240904392704 |
---|---|
author | Feng Xia Li Kaiye Wu Songze Xin yan |
author_facet | Feng Xia Li Kaiye Wu Songze Xin yan |
author_sort | Feng Xia |
collection | DOAJ |
description | Abstract The use of federated learning to achieve blockchain interoperability has become a hot topic in research, because it enables data exchange without revealing any private information. However, the previous work, such as ScaleSFL (Asia‐CCS, 2022), that has implemented federated learning for blockchain interoperability, the throughput of the framework still cannot support the practical applications. Therefore, a federated learning framework based on Directed Acyclic Graph (DAG) is proposed which utilizes sharding mechanism to enhance the blockchain interoperability. By constructing a weighted context graph based on data correlation, reasonable sharding of the dataset is achieved, thereby improving the efficiency of blockchain interoperability. The experimental results show that the federated framework reduces global computation in federated learning by 30% compared with other schemes, while increasing blockchain throughput by nearly 40%. |
first_indexed | 2024-03-09T10:45:20Z |
format | Article |
id | doaj.art-46bdd48105314e57b67b0a7f8b165879 |
institution | Directory Open Access Journal |
issn | 2634-1573 |
language | English |
last_indexed | 2024-03-09T10:45:20Z |
publishDate | 2023-12-01 |
publisher | Wiley |
record_format | Article |
series | IET Blockchain |
spelling | doaj.art-46bdd48105314e57b67b0a7f8b1658792023-12-01T10:35:00ZengWileyIET Blockchain2634-15732023-12-013423824810.1049/blc2.12033Enhancing the blockchain interoperability through federated learning with directed acyclic graphFeng Xia0Li Kaiye1Wu Songze2Xin yan3Faculty of Data Science City University of Macau Avenida Padre Tomás Pereira Macau ChinaFaculty of Data Science City University of Macau Avenida Padre Tomás Pereira Macau ChinaFaculty of Data Science City University of Macau Avenida Padre Tomás Pereira Macau ChinaSchool of Computer Science and Communication Engineering Jiangsu Univestity Zhenjiang ChinaAbstract The use of federated learning to achieve blockchain interoperability has become a hot topic in research, because it enables data exchange without revealing any private information. However, the previous work, such as ScaleSFL (Asia‐CCS, 2022), that has implemented federated learning for blockchain interoperability, the throughput of the framework still cannot support the practical applications. Therefore, a federated learning framework based on Directed Acyclic Graph (DAG) is proposed which utilizes sharding mechanism to enhance the blockchain interoperability. By constructing a weighted context graph based on data correlation, reasonable sharding of the dataset is achieved, thereby improving the efficiency of blockchain interoperability. The experimental results show that the federated framework reduces global computation in federated learning by 30% compared with other schemes, while increasing blockchain throughput by nearly 40%.https://doi.org/10.1049/blc2.12033blockchainsblockchain applications and digital technologydata privacydata protection |
spellingShingle | Feng Xia Li Kaiye Wu Songze Xin yan Enhancing the blockchain interoperability through federated learning with directed acyclic graph IET Blockchain blockchains blockchain applications and digital technology data privacy data protection |
title | Enhancing the blockchain interoperability through federated learning with directed acyclic graph |
title_full | Enhancing the blockchain interoperability through federated learning with directed acyclic graph |
title_fullStr | Enhancing the blockchain interoperability through federated learning with directed acyclic graph |
title_full_unstemmed | Enhancing the blockchain interoperability through federated learning with directed acyclic graph |
title_short | Enhancing the blockchain interoperability through federated learning with directed acyclic graph |
title_sort | enhancing the blockchain interoperability through federated learning with directed acyclic graph |
topic | blockchains blockchain applications and digital technology data privacy data protection |
url | https://doi.org/10.1049/blc2.12033 |
work_keys_str_mv | AT fengxia enhancingtheblockchaininteroperabilitythroughfederatedlearningwithdirectedacyclicgraph AT likaiye enhancingtheblockchaininteroperabilitythroughfederatedlearningwithdirectedacyclicgraph AT wusongze enhancingtheblockchaininteroperabilitythroughfederatedlearningwithdirectedacyclicgraph AT xinyan enhancingtheblockchaininteroperabilitythroughfederatedlearningwithdirectedacyclicgraph |