Multi-Attribute Selectivity Estimation Using Deep Learning

TL;DR

This paper explores deep learning methods for multi-attribute selectivity estimation in databases, introducing unsupervised density estimation and supervised prediction approaches to improve accuracy and efficiency.

Contribution

It presents novel deep learning techniques for selectivity estimation, addressing practical challenges and demonstrating superior performance over traditional methods.

Findings

Deep density estimation effectively models joint attribute distributions.

Supervised deep learning accurately predicts query selectivity.

Proposed methods outperform existing techniques in speed and accuracy.

Abstract

Selectivity estimation - the problem of estimating the result size of queries - is a fundamental problem in databases. Accurate estimation of query selectivity involving multiple correlated attributes is especially challenging. Poor cardinality estimates could result in the selection of bad plans by the query optimizer. We investigate the feasibility of using deep learning based approaches for both point and range queries and propose two complementary approaches. Our first approach considers selectivity as an unsupervised deep density estimation problem. We successfully introduce techniques from neural density estimation for this purpose. The key idea is to decompose the joint distribution into a set of tractable conditional probability distributions such that they satisfy the autoregressive property. Our second approach formulates selectivity estimation as a supervised deep learning problem that predicts the selectivity of a given query. We also introduce and address a number of practical challenges arising when adapting deep learning for relational data. These include query/data featurization, incorporating query workload information in a deep learning framework and the dynamic scenario where both data and workload queries could be updated. Our extensive experiments with a special emphasis on queries with a large number of predicates and/or small result sizes demonstrates that our proposed techniques provide fast and accurate selective estimates with minimal space overhead.