2020/03/05 by Meifan Zhang, Zhang, Meifan, Hongzhi Wang +1 · 2 citations
Computer Science · Mathematics · #Advanced Database Systems and Queries #Artificial intelligence #Big data #Computer science #Data Management and Algorithms #Data Stream Mining Techniques #Data mining #Databases (cs.DB) #FOS: Computer and information sciences #Line (geometry) #Machine Learning (cs.LG) #Machine learning #Mathematics #Query optimization #Sample (material) #Sampling (signal processing) #Task (project management) #cs.DB #cs.LG
paper · pdf · doi:10.48550/arxiv.2003.02446
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/03/05 · openalex publication_date 2020/03/05 · arxiv updated 2020/03/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Querying on big data is a challenging task due to the rapid growth of data amount. Approximate query processing (AQP) is a way to meet the requirement of fast response. In this paper, we propose a learning-based AQP method called the LAQP. The LAQP builds an error model learned from the historical queries to predict the sampling-based estimation error of each new query. It makes a combination of the sampling-based AQP, the pre-computed aggregations and the learned error model to provide high-accurate query estimations with a small off-line sample. The experimental results indicate that our LAQP outperforms the sampling-based AQP, the pre-aggregation-based AQP and the most recent learning-based AQP method.