Poster: Blockchain-Enabled Federated Edge Learning for Big Data Quality Assessment

Abstract

Data quality is essential to pricing big data and deciding its trading profit in digital market. Traditional machine learning-based data quality assessment methods support the valuation of data assets. Nonetheless, these methods require data to be sent over and assessed at centralized cloud, which incurs unprecedented data transmission cost and may jeopardize data privacy. To address these issues, in this poster, we propose a privacy-preserving big data quality assessment scheme (p2 QA) on the basis of blockchain and federated edge learning (FEEL). p2QA aims to notably reduce data transmission cost, accurately measure big data quality, and effectively prevent malicious parties from violating data privacy.