An Empirical Analysis of Deep Learning for Cardinality Estimation

05/15/2019
by   Jennifer Ortiz, et al.
0

We implement and evaluate deep learning for cardinality estimation by studying the accuracy, space and time trade-offs across several architectures. We find that simple deep learning models can learn cardinality estimations across a variety of datasets (reducing the error by 72 compared to PostgreSQL). In addition, we empirically evaluate the impact of injecting cardinality estimates produced by deep learning models into the PostgreSQL optimizer. In many cases, the estimates from these models lead to better query plans across all datasets, reducing the runtimes by up to 49 select-project-join workloads. As promising as these models are, we also discuss and address some of the challenges of using them in practice.

READ FULL TEXT
research
11/17/2022

SafeBound: A Practical System for Generating Cardinality Bounds

Recent work has reemphasized the importance of cardinality estimates for...
research
09/03/2018

Learned Cardinalities: Estimating Correlated Joins with Deep Learning

We describe a new deep learning approach to cardinality estimation. MSCN...
research
02/21/2021

LMKG: Learned Models for Cardinality Estimation in Knowledge Graphs

Accurate cardinality estimates are a key ingredient to achieve optimal q...
research
02/16/2023

Reducing Computational and Statistical Complexity in Machine Learning Through Cardinality Sparsity

High-dimensional data has become ubiquitous across the sciences but caus...
research
02/15/2020

Monotonic Cardinality Estimation of Similarity Selection: A Deep Learning Approach

Due to the outstanding capability of capturing underlying data distribut...
research
01/13/2021

Flow-Loss: Learning Cardinality Estimates That Matter

Previous approaches to learned cardinality estimation have focused on im...
research
06/06/2019

An End-to-End Learning-based Cost Estimator

Cost and cardinality estimation is vital to query optimizer, which can g...

Please sign up or login with your details

Forgot password? Click here to reset