MatSwarm: trusted swarm transfer learning driven materials computation for secure big data sharing

Ran Wang, Cheng Xu (), Shuhao Zhang, Fangwen Ye, Yusen Tang, Sisui Tang, Hangning Zhang, Wendi Du and Xiaotong Zhang ()
Additional contact information
Ran Wang: University of Science and Technology Beijing
Cheng Xu: University of Science and Technology Beijing
Shuhao Zhang: Nanyang Technological University
Fangwen Ye: University of Science and Technology Beijing
Yusen Tang: University of Science and Technology Beijing
Sisui Tang: University of Science and Technology Beijing
Hangning Zhang: University of Science and Technology Beijing
Wendi Du: University of Science and Technology Beijing
Xiaotong Zhang: University of Science and Technology Beijing

Nature Communications, 2024, vol. 15, issue 1, 1-14

Abstract: Abstract The rapid advancement of Industry 4.0 necessitates close collaboration among material research institutions to accelerate the development of novel materials. However, multi-institutional cooperation faces significant challenges in protecting sensitive data, leading to data silos. Additionally, the heterogeneous and non-independent and identically distributed (non-i.i.d.) nature of material data hinders model accuracy and generalization in collaborative computing. In this paper, we introduce the MatSwarm framework, built on swarm learning, which integrates federated learning with blockchain technology. MatSwarm features two key innovations: a swarm transfer learning method with a regularization term to enhance the alignment of local model parameters, and the use of Trusted Execution Environments (TEE) with Intel SGX for heightened security. These advancements significantly enhance accuracy, generalization, and ensure data confidentiality throughout the model training and aggregation processes. Implemented within the National Material Data Management and Services (NMDMS) platform, MatSwarm has successfully aggregated over 14 million material data entries from more than thirty research institutions across China. The framework has demonstrated superior accuracy and generalization compared to models trained independently by individual institutions.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-53431-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-53431-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-53431-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().