Multi-Technology Fused Data Trading Method Based on Federated Learning
The constraints of data protection have restricted data within different enterprises and organizations,forming several"data islands"that make it difficult to tap into their inherent important value.The emergence of Federated Learning(FL)has made data sharing between organizations possible.However,issues such as unclear benefit distribution schemes,high communication costs,and centralization make it difficult to meet the multifaceted demands of data trading scenarios.To address these issues,a Multi-Technology Fused Data Trading(MTFDT)method based on FL is proposed.In this method,the incentive mechanism is designed by combining trusted execution environments with the Shapley value.The model and data synchronization mechanism during trading are optimized using a tree-based topological structure-based model synchronization scheme,reducing the synchronization time complexity from linear to logarithmic.Simultaneously,blockchain-based benefit distribution data and model data storage solutions are designed to make the transaction information tamper-proof and accountable through traceability.Finally,simulations and comparisons are performed using public datasets.The experimental results demonstrate that MTFDT can achieve a precise evaluation of the model training effects and improve the fairness of the benefit distribution.Compared to existing solutions,the time consumption of model synchronization is reduced by up to 34%,and the bandwidth requirement is lower.
data transactionFederated Learning(FL)blockchainincentive systemcommunication optimization
国家科技期刊平台
NSTL
万方数据
