A BiLSTM cardinality estimator in complex database systems based on attention mechanism

CAAI Transactions on Intelligence Technology

article

Qiang Zhou¹  Guoping Yang²  Haiquan Song³  Jin Guo¹  Yadong Zhang¹  Shengjie Wei⁴  Lulu Qu²  Louis Alberto Gutierrez⁵  Shaojie Qiao² 

[1] School of Information Science and Technology, Southwest Jiaotong University;School of Software Engineering, Chengdu University of Information Technology;School of Energy Power and Mechanical Engineering, North China Electric Power University;Digital Media Art, Key Laboratory of Sichuan Province;Department of Computer Science, Rensselaer Polytechnic Institute

关键词: attention;    BiLSTM;    cardinality estimation;    complex database systems;    query optimiser;    Word2vec;    query processing;    database management systems;    recurrent neural nets;    deep learning (artificial intelligence);    estimation theory;   

DOI  :  10.1049/cit2.12069

学科分类：数学（综合）

来源: Wiley

【 摘 要 】

An excellent cardinality estimation can make the query optimiser produce a good execution plan. Although there are some studies on cardinality estimation, the prediction results of existing cardinality estimators are inaccurate and the query efficiency cannot be guaranteed as well. In particular, they are difficult to accurately obtain the complex relationships between multiple tables in complex database systems. When dealing with complex queries, the existing cardinality estimators cannot achieve good results. In this study, a novel cardinality estimator is proposed. It uses the core techniques with the BiLSTM network structure and adds the attention mechanism. First, the columns involved in the query statements in the training set are sampled and compressed into bitmaps. Then, the Word2vec model is used to embed the word vectors about the query statements. Finally, the BiLSTM network and attention mechanism are employed to deal with word vectors. The proposed model takes into consideration not only the correlation between tables but also the processing of complex predicates. Extensive experiments and the evaluation of BiLSTM-Attention Cardinality Estimator (BACE) on the IMDB datasets are conducted. The results show that the deep learning model can significantly improve the quality of cardinality estimation, which is a vital role in query optimisation for complex databases.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND