mlsanityData to 7 Oct 2026

Learned Cardinalities: Estimating Correlated Joins with Deep Learning

arXiv 1809.00677 ↗First posted 3 Sep 2018cs.DBcited by 64

Not on the map. Why?

Abstract (arXiv)

We describe a new deep learning approach to cardinality estimation. MSCN is a multi-set convolutional network, tailored to representing relational query plans, that employs set semantics to capture query features and true cardinalities. MSCN builds on sampling-based estimation, addressing its weaknesses when no sampled tuples qualify a predicate, and in capturing join-crossing correlations. Our evaluation of MSCN using a real-world dataset shows that deep learning significantly enhances the quality of cardinality estimation, which is the core problem in query optimization.

Key facts. Cited by 64 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 9; 2023: 8; 2024: 10; 2025: 18; 2026: 7.

64 papers.

Sort:

By area:

  1. 2021Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluationcited by 30
  2. 2023Lero: A Learning-to-Rank Query Optimizercited by 26
  3. 2021A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimationcited by 21
  4. 2022Balsa: Learning a Query Optimizer Without Expert Demonstrationscited by 18
  5. 2022Zero-Shot Cost Models for Out-of-the-box Learned Cost Predictioncited by 16
  6. 2021A Survey on Advancing the DBMS Query Optimizer: Cardinality Estimation, Cost Model, and Plan Enumerationcited by 14
  7. 2022FactorJoin: A New Cardinality Estimation Framework for Join Queriescited by 13
  8. 2025Cortex AISQL: A Production SQL Engine for Unstructured Datacited by 11
  9. 2021A Unified Transferable Model for ML-Enhanced DBMScited by 10
  10. 2021One Model to Rule them All: Towards Zero-Shot Learning for Databasescited by 9
  11. 2021CARMI: A Cache-Aware Learned Index with a Cost-based Construction Algorithmcited by 8
  12. 2024PRICE: A Pretrained Model for Cross-Database Cardinality Estimationcited by 8
38 more
  1. 2022Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Datacited by 6
  2. 2022CodexDB: Generating Code for Processing SQL Queries using GPT-3 Codexcited by 5
  3. 2021Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workloadcited by 4
  4. 2021No DBA? No regret! Multi-armed bandits for index tuning of analytical and HTAP workloads with provable guaranteescited by 4
  5. 2022Learning to be a Statistician: Learned Estimator for Number of Distinct Valuescited by 4
  6. 2024CardBench: A Benchmark for Learned Cardinality Estimation in Relational Databasescited by 4
  7. 2024The Unreasonable Effectiveness of LLMs for Query Optimizationcited by 4
  8. 2024Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnabilitycited by 4
  9. 2025RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systemscited by 4
  10. 2023Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networkscited by 3
  11. 2023Kepler: Robust Learning for Faster Parametric Query Optimizationcited by 3
  12. 2023Duet: efficient and scalable hybriD neUral rElation undersTandingcited by 3
  13. 2024A Practical Theory of Generalization in Selectivity Learningcited by 3
  14. 2024HERO: Hint-Based Efficient and Reliable Query Optimizercited by 3
  15. 2021Can Deep Neural Networks Predict Data Correlations from Column Names?cited by 2
  16. 2021Glue: Adaptively Merging Single Table Cardinality to Estimate Join Query Sizecited by 2
  17. 2023Serving Deep Learning Model in Relational Databasescited by 2
  18. 2024Towards Establishing Guaranteed Error for Learned Database Operationscited by 2
  19. 2026AI-Driven Research for Databasescited by 2
  20. 2021A Pluggable Learned Index Method via Sampling and Gap Insertioncited by 1
  21. 2021Phoebe: A Learning-based Checkpoint Optimizercited by 1
  22. 2023JoinGym: An Efficient Query Optimization Environment for Reinforcement Learningcited by 1
  23. 2024GenJoin: Conditional Generative Plan-to-Plan Query Optimizer that Learns from Subplan Hintscited by 1
  24. 2024CardOOD: Robust Query-driven Cardinality Estimation under Out-of-Distributioncited by 1
  25. 2025DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulationcited by 1
  26. 2025Data-Agnostic Cardinality Learning from Imperfect Workloadscited by 1
  27. 2025Is it Bigger than a Breadbox: Efficient Cardinality Estimation for Real World Workloadscited by 1
  28. 2026BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQLcited by 1
  29. 2022Multi-agent Databases via Independent Learningcited by 0
  30. 2022Model Joins: Enabling Analytics Over Joins of Absent Big Tablescited by 0
  31. 2022Optimal consumption-investment choices under wealth-driven risk aversioncited by 0
  32. 2023Scardina: Scalable Join Cardinality Estimation by Multiple Density Estimatorscited by 0
  33. 2023BitE : Accelerating Learned Query Optimization in a Mixed-Workload Environmentcited by 0
  34. 2024LearnedWMP: Workload Memory Prediction Using Distribution of Query Templatescited by 0
  35. 2025Optimize Cardinality Estimation Model Pretraining by Simplifying the Training Datasetscited by 0
  36. 2025Selective Use of Yannakakis' Algorithm to Improve Query Performance: Machine Learning to the Rescuecited by 0
  37. 2025Low Rank Learning for Offline Query Optimizationcited by 0
  38. 2025Training-Free Query Optimization via LLM-Based Plan Similaritycited by 0

50 most cited of 64 All 64 (JSON)