A Lightweight Learned Cardinality Estimation Model
By: Yaoyu Zhu , Jintao Zhang , Guoliang Li and more
Potential Business Impact:
Makes computer databases guess answers faster and better.
Cardinality estimation is a fundamental task in database management systems, aiming to predict query results accurately without executing the queries. However, existing techniques either achieve low estimation accuracy or incur high inference latency. Simultaneously achieving high speed and accuracy becomes critical for the cardinality estimation problem. In this paper, we propose a novel data-driven approach called CoDe (Covering with Decompositions) to address this problem. CoDe employs the concept of covering design, which divides the table into multiple smaller, overlapping segments. For each segment, CoDe utilizes tensor decomposition to accurately model its data distribution. Moreover, CoDe introduces innovative algorithms to select the best-fitting distributions for each query, combining them to estimate the final result. By employing multiple models to approximate distributions, CoDe excels in effectively modeling discrete distributions and ensuring computational efficiency. Notably, experimental results show that our method represents a significant advancement in cardinality estimation, achieving state-of-the-art levels of both estimation accuracy and inference efficiency. Across various datasets, CoDe achieves absolute accuracy in estimating more than half of the queries.
Similar Papers
CUBE: A Cardinality Estimator Based on Neural CDF
Databases
Makes computer searches faster and more reliable.
Data-Agnostic Cardinality Learning from Imperfect Workloads
Databases
Helps computers guess data size without seeing data.
ACE: A Cardinality Estimator for Set-Valued Queries
Databases
Helps computers guess how many results a search will have.