# Are We Ready For Learned Cardinality Estimation?

arXiv: https://arxiv.org/abs/2012.06743 · HTML: https://mlsanity.com/paper/2012.06743/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2020.

## Built on by (most cited first, 19 of 19)

- [Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation](https://mlsanity.com/paper/2109.05877/) (2021)
- [Lero: A Learning-to-Rank Query Optimizer](https://mlsanity.com/paper/2302.06873/) (2023)
- [Balsa: Learning a Query Optimizer Without Expert Demonstrations](https://mlsanity.com/paper/2201.01441/) (2022)
- [A Unified Transferable Model for ML-Enhanced DBMS](https://mlsanity.com/paper/2105.02418/) (2021)
- [PRICE: A Pretrained Model for Cross-Database Cardinality Estimation](https://mlsanity.com/paper/2406.01027/) (2024)
- [Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data](https://mlsanity.com/paper/2210.05508/) (2022)
- [WISK: A Workload-aware Learned Index for Spatial Keyword Queries](https://mlsanity.com/paper/2302.14287/) (2023)
- [Learning to be a Statistician: Learned Estimator for Number of Distinct Values](https://mlsanity.com/paper/2202.02800/) (2022)
- [Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability](https://mlsanity.com/paper/2411.06241/) (2024)
- [Kepler: Robust Learning for Faster Parametric Query Optimization](https://mlsanity.com/paper/2306.06798/) (2023)
- [Duet: efficient and scalable hybriD neUral rElation undersTanding](https://mlsanity.com/paper/2307.13494/) (2023)
- [CAMAL: Optimizing LSM-trees via Active Learning](https://mlsanity.com/paper/2409.15130/) (2024)
- [CardOOD: Robust Query-driven Cardinality Estimation under Out-of-Distribution](https://mlsanity.com/paper/2412.05864/) (2024)
- [DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulation](https://mlsanity.com/paper/2503.08994/) (2025)
- [Is it Bigger than a Breadbox: Efficient Cardinality Estimation for Real World Workloads](https://mlsanity.com/paper/2510.03386/) (2025)
- [CoLSE: A Lightweight and Robust Hybrid Learned Model for Single-Table Cardinality Estimation using Joint CDF](https://mlsanity.com/paper/2512.12624/) (2025)
- [MICRO: A Lightweight Middleware for Optimizing Cross-store Cross-model Graph-Relation Joins [Technical Report]](https://mlsanity.com/paper/2603.13835/) (2026)
- [Selectivity Estimation for Linear Queries via Online Learning](https://mlsanity.com/paper/2607.02895/) (2026)
- [Learning-Augmented Algorithms: Guarantees, Construction Mechanisms, and System-Level Implications](https://mlsanity.com/paper/2609.04787/) (2026)

## Abstract (arXiv)

Cardinality estimation is a fundamental but long unresolved problem in query optimization. Recently, multiple papers from different research groups consistently report that learned models have the potential to replace existing cardinality estimators. In this paper, we ask a forward-thinking question: Are we ready to deploy these learned cardinality models in production? Our study consists of three main parts. Firstly, we focus on the static environment (i.e., no data updates) and compare five new learned methods with eight traditional methods on four real-world datasets under a unified workload setting. The results show that learned models are indeed more accurate than traditional methods, but they often suffer from high training and inference costs. Secondly, we explore whether these learned models are ready for dynamic environments (i.e., frequent data updates). We find that they cannot catch up with fast data up-dates and return large errors for different reasons. For less frequent updates, they can perform better but there is no clear winner among themselves. Thirdly, we take a deeper look into learned models and explore when they may go wrong. Our results show that the performance of learned methods can be greatly affected by the changes in correlation, skewness, or domain size. More importantly, their behaviors are much harder to interpret and often unpredictable. Based on these findings, we identify two promising research directions (control the cost of learned models and make learned models trustworthy) and suggest a number of research opportunities. We hope that our study can guide researchers and practitioners to work together to eventually push learned cardinality estimators into real database systems.