Learned Cardinalities: Estimating Correlated Joins with Deep Learning

Summary: Proposes MSCN, a multi-set convolutional network that encodes relational query plans with set semantics to learn cardinalities and capture join-crossing correlations. Combines deep learning with sampling to handle zero-sample cases, yielding much better estimates on real-world data. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 314
Venue: CIDR
Year: 2019
Pagerank: 0.00035838391
Overall Rank: 84 | 99.43%
DOI: -

Incoming Non-self Citations Over Time

Authors

1. Andreas Kipf (Technical University of Munich)
2. Thomas Kipf (University of Amsterdam)
3. Bernhard Radke (Technical University of Munich)
4. Viktor Leis (Technical University of Munich)
5. Peter Boncz (Centrum Wiskunde & Informatica)
6. Alfons Kemper (Technical University of Munich)

BibTeX Citation

@inproceedings{kipf_cidr19,
        address = {Amsterdam, Netherlands},
        series = {{CIDR} '19},
        title = {{Learned Cardinalities: Estimating Correlated Joins with Deep Learning}},
        booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
        author = {Kipf, Andreas and Kipf, Thomas and Radke, Bernhard and Leis, Viktor and Boncz, Peter and Kemper, Alfons},
        year = {2019}
}

Incoming Citations (Sorted by Pagerank)

Showing 50 of 180 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
7,213	Scalable Multi-Query Execution using Reinforcement Learning	2021	SIGMOD	5.670422e-05
7,268	Cardinality Estimation of Approximate Substring Queries using Deep Learning	2022	VLDB	5.6597123e-05
7,290	Learning to be a Statistician: Learned Estimator for Number of Distinct Values	2022	VLDB	5.6540503e-05
7,787	A Practical Approach to Groupjoin and Nested Aggregates	2021	VLDB	5.5449593e-05
7,825	RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems	2025	VLDB	5.5367884e-05
7,829	Robust Query Processing: Mission Possible	2020	VLDB	5.5360082e-05
7,910	Quantum-Inspired Digital Annealing for Join Ordering	2024	VLDB	5.5181056e-05
8,040	PerfGuard: Deploying ML-for-Systems without Performance Regressions, Almost!	2021	VLDB	5.5018396e-05
8,124	Consistent and Flexible Selectivity Estimation for High-Dimensional Data	2021	SIGMOD	5.4829513e-05
8,127	The Case for NLP-Enhanced Database Tuning: Towards Tuning Tools that “Read the Manual”	2021	VLDB	5.4826853e-05
8,163	Learned Offline Query Planning via Bayesian Optimization	2025	SIGMOD	5.4751517e-05
8,234	The Case for Learned In-Memory Joins	2023	VLDB	5.460955e-05
8,305	PARQO: Penalty-Aware Robust Plan Selection in Query Optimization	2024	VLDB	5.4568571e-05
8,413	Conditional Cuckoo Filters	2021	SIGMOD	5.4306049e-05
8,492	ShadowAQP: Efficient Approximate Group-by and Join Query via Attribute-oriented Sample Size Allocation and Data Generation	2023	VLDB	5.4145838e-05
8,494	POLAR: Adaptive and Non-invasive Join Order Selection via Plans of Least Resistance	2024	VLDB	5.4142129e-05
8,572	T3: Accurate and Fast Performance Prediction for Relational Database Systems With Compiled Decision Trees	2025	SIGMOD	5.4102362e-05
8,643	PACE: Poisoning Attacks on Learned Cardinality Estimation	2024	SIGMOD	5.3940849e-05
8,698	SkinnerMT: Parallelizing for Efficiency and Robustness in Adaptive Query Processing on Multicore Platforms	2023	VLDB	5.3830073e-05
8,791	HAP: An Efficient Hamming Space Index Based on Augmented Pigeonhole Principle	2022	SIGMOD	5.3717005e-05
8,849	ByteCard: Enhancing ByteDance’s Data Warehouse with Learned Cardinality Estimation	2024	SIGMOD	5.3577504e-05
8,854	Towards Foundation Database Models	2025	CIDR	5.357608e-05
9,101	NeuroSketch: Fast and Approximate Evaluation of Range Aggregate Queries with Neural Networks	2023	SIGMOD	5.324758e-05
9,106	AirIndex: Versatile Index Tuning Through Data and Storage	2023	SIGMOD	5.3226167e-05
9,112	Towards Enhancing Database Education: Natural Language Generation Meets Query Execution Plans	2021	SIGMOD	5.3218986e-05
9,192	Efficient and Effective Cardinality Estimation for Skyline Family	2023	SIGMOD	5.3058708e-05
9,224	Phoebe: A Learning-based Checkpoint Optimizer	2021	VLDB	5.3035811e-05
9,428	LIMAO: A Framework for Lifelong Modular Learned Query Optimization	2025	VLDB	5.2709145e-05
9,455	Small Selectivities Matter: Lifting the Burden of Empty Samples	2021	SIGMOD	5.2653318e-05
9,491	CEDA: Learned Cardinality Estimation with Domain Adaptation	2023	VLDB	5.2626014e-05
9,587	Machine Unlearning in Learned Databases: An Experimental Analysis	2024	SIGMOD	5.2525104e-05
9,601	Low Rank Learning for Offline Query Optimization	2025	SIGMOD	5.2487799e-05
9,617	NeuSO: Neural Optimizer for Subgraph Queries	2026	SIGMOD	5.2434488e-05
9,724	Approximate Sketches	2024	SIGMOD	5.2308295e-05
9,756	Efficient Query Re-optimization with Judicious Subquery Selections	2023	SIGMOD	5.2258278e-05
9,793	Selectivity Estimation for Queries Containing Predicates over Set-Valued Attributes	2023	SIGMOD	5.2193018e-05
9,796	ROME: Robust Query Optimization via Parallel Multi-Plan Execution	2024	SIGMOD	5.21848e-05
9,844	Cardinality Estimation of LIKE Predicate Queries using Deep Learning	2025	SIGMOD	5.2094602e-05
9,867	SPACE: Cardinality Estimation for Path Queries Using Cardinality-Aware Sequence-based Learning	2025	SIGMOD	5.2043672e-05
9,920	Still Asking: How Good Are Query Optimizers, Really?	2025	VLDB	5.1955087e-05
9,958	A Practical Theory of Generalization in Selectivity Learning	2025	VLDB	5.1879626e-05
9,966	Generating Application-Specific Data Layouts for In-memory Databases	2019	VLDB	5.1870939e-05
9,971	Athena: An Effective Learning-based Framework for Query Optimizer Performance Improvement	2025	SIGMOD	5.1845938e-05
9,996	Path-centric Cardinality Estimation for Subgraph Matching	2025	VLDB	5.1814573e-05
10,016	Turbo-Charging SPJ Query Plans with Learned Physical Join Operator Selections	2022	VLDB	5.1764556e-05
10,028	PRICE: A Pretrained Model for Cross-Database Cardinality Estimation	2025	VLDB	5.1745962e-05
10,041	DBMS Fitting: Why should we learn what we already know?	2020	CIDR	5.1709251e-05
10,097	SSCard: Substring Cardinality Estimation using Suffix Tree-Guided Learned FM-Index	2026	SIGMOD	5.1502319e-05
10,108	An Elephant Under The Microscope: Analyzing The Interaction Of Optimizer Components In PostgreSQL	2025	SIGMOD	5.1347137e-05
10,196	Are Learned DBMS Components Robust to Workload Drift?: [Experiments & Analysis]	2026	SIGMOD	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 14 of 14 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
18	How Good Are Query Optimizers, Really?	2016	VLDB	0.00059284255
43	The Case for Learned Index Structures	2018	SIGMOD	0.00046060254
86	Automatic Database Management System Tuning Through Large-scale Machine Learning	2017	SIGMOD	0.00035316107
101	Selectivity Estimation Without the Attribute Value Independence Assumption	1997	VLDB	0.00034376651
388	Preventing Bad Plans by Bounding the Impact of Cardinality Estimation Errors	2009	VLDB	0.00019410042
682	Robust Estimation of Resource Consumption for SQL Queries using Statistical Techniques	2012	VLDB	0.00015014887
694	Cardinality Estimation Done Right: Index-Based Join Sampling	2017	CIDR	0.00014911698
737	Join Size Estimation Subject to Filter Conditions	2015	VLDB	0.00014490983
1,256	Sampling-Based Query Re-Optimization	2016	SIGMOD	0.00011457194
1,286	Adaptive Optimization of Very Large Join Queries	2018	SIGMOD	0.00011320736
1,536	Improved Selectivity Estimation by Combining Knowledge from Sampling and Synopses	2018	VLDB	0.00010460864
1,664	Two-Level Sampling for Join Size Estimation	2017	SIGMOD	0.00010070362
2,157	A Black-Box Approach to Query Cardinality Estimation	2007	CIDR	9.0625592e-05
2,281	Selectivity Estimation in Extensible Databases - A Neural Network Approach	1998	VLDB	8.8129279e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	401	Deep Unsupervised Cardinality Estimation	2020	VLDB
2	1,061	Are We Ready For Learned Cardinality Estimation?	2021	VLDB
3	1,573	Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries	2020	SIGMOD
4	7,268	Cardinality Estimation of Approximate Substring Queries using Deep Learning	2022	VLDB
5	6,341	Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks	2024	SIGMOD
6	9,844	Cardinality Estimation of LIKE Predicate Queries using Deep Learning	2025	SIGMOD
7	2,543	Learned Cardinality Estimation: An In-depth Study	2022	SIGMOD
8	4,617	Learned Cardinality Estimation for Similarity Queries	2021	SIGMOD
9	5,712	Sample-Efficient Cardinality Estimation Using Geometric Deep Learning	2024	VLDB
10	2,723	Learned Cardinality Estimation: A Design Space Exploration and A Comparative Evaluation	2022	VLDB