CUBE: A Cardinality Estimator Based on Neural CDF

TL;DR

This paper introduces CUBE, a neural CDF-based cardinality estimator that provides fast, accurate, and scalable range query estimates without sampling, outperforming existing data-driven methods in speed and stability.

Contribution

CUBE is the first neural CDF-based cardinality estimator that guarantees low-latency, high-accuracy, and scalability for high-dimensional data without sampling or integration.

Findings

Over 10x faster inference than state-of-the-art methods

Maintains high accuracy across increasing data dimensionality

Provides stable and predictable estimation results

Abstract

Modern database optimizer relies on cardinality estimator, whose accuracy directly affects the optimizer's ability to choose an optimal execution plan. Recent work on data-driven methods has leveraged probabilistic models to achieve higher estimation accuracy, but these approaches cannot guarantee low inference latency at the same time and neglect scalability. As data dimensionality grows, optimization time can even exceed actual query execution time. Furthermore, inference with probabilistic models by sampling or integration procedures unpredictable estimation result and violate stability, which brings unstable performance with query execution and make database tuning hard for database users. In this paper, we propose a novel approach to cardinality estimation based on cumulative distribution function(CDF), which calculates range query cardinality without sampling or integration, ensuring accurate and predictable estimation results. With inference acceleration by merging calculations, we can achieve fast and nearly constant inference speed while maintaining high accuracy, even as dimensionality increases, which is over 10x faster than current state-of-the-art data-driven cardinality estimator. This demonstrates its excellent dimensional scalability, making it well-suited for real-world database applications.