# DeepDB: Learn from Data, not from Queries!

arXiv: https://arxiv.org/abs/1909.00607 · HTML: https://mlsanity.com/paper/1909.00607/

## Key facts

- Cited by 20 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 2 Sep 2019.

## Built on by (most cited first, 20 of 20)

- [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)
- [A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation](https://mlsanity.com/paper/2107.12295/) (2021)
- [Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction](https://mlsanity.com/paper/2201.00561/) (2022)
- [Cortex AISQL: A Production SQL Engine for Unstructured Data](https://mlsanity.com/paper/2511.07663/) (2025)
- [One Model to Rule them All: Towards Zero-Shot Learning for Databases](https://mlsanity.com/paper/2105.00642/) (2021)
- [PRICE: A Pretrained Model for Cross-Database Cardinality Estimation](https://mlsanity.com/paper/2406.01027/) (2024)
- [Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks](https://mlsanity.com/paper/2303.01140/) (2023)
- [Duet: efficient and scalable hybriD neUral rElation undersTanding](https://mlsanity.com/paper/2307.13494/) (2023)
- [A Practical Theory of Generalization in Selectivity Learning](https://mlsanity.com/paper/2409.07014/) (2024)
- [Electra: Conditional Generative Model based Predicate-Aware Query Approximation](https://mlsanity.com/paper/2201.12420/) (2022)
- [Robust Plan Evaluation based on Approximate Probabilistic Machine Learning](https://mlsanity.com/paper/2401.15210/) (2024)
- [CardOOD: Robust Query-driven Cardinality Estimation under Out-of-Distribution](https://mlsanity.com/paper/2412.05864/) (2024)
- [Data-Agnostic Cardinality Learning from Imperfect Workloads](https://mlsanity.com/paper/2506.16007/) (2025)
- [Baihe: SysML Framework for AI-driven Databases](https://mlsanity.com/paper/2112.14460/) (2021)
- [Scardina: Scalable Join Cardinality Estimation by Multiple Density Estimators](https://mlsanity.com/paper/2303.18042/) (2023)
- [ACE: A Cardinality Estimator for Set-Valued Queries](https://mlsanity.com/paper/2503.14929/) (2025)
- [BQSched: A Non-intrusive Scheduler for Batch Concurrent Queries via Reinforcement Learning](https://mlsanity.com/paper/2504.19142/) (2025)
- [Exqutor: Extended Query Optimizer for Vector-augmented Analytical Queries](https://mlsanity.com/paper/2512.09695/) (2025)
- [CoLSE: A Lightweight and Robust Hybrid Learned Model for Single-Table Cardinality Estimation using Joint CDF](https://mlsanity.com/paper/2512.12624/) (2025)

## Abstract (arXiv)

The typical approach for learned DBMS components is to capture the behavior by running a representative set of queries and use the observations to train a machine learning model. This workload-driven approach, however, has two major downsides. First, collecting the training data can be very expensive, since all queries need to be executed on potentially large databases. Second, training data has to be recollected when the workload and the data changes. To overcome these limitations, we take a different route: we propose to learn a pure data-driven model that can be used for different tasks such as query answering or cardinality estimation. This data-driven model also supports ad-hoc queries and updates of the data without the need of full retraining when the workload or data changes. Indeed, one may now expect that this comes at a price of lower accuracy since workload-driven models can make use of more information. However, this is not the case. The results of our empirical evaluation demonstrate that our data-driven approach not only provides better accuracy than state-of-the-art learned components but also generalizes better to unseen queries.