How Good are Learned Cost Models, Really? Insights from Query Optimization Tasks

Summary: Systematic evaluation of Learned Cost Models for query optimization across main tasks: join ordering, access path, and operator choice. Seven LCMs vs traditional models; surprisingly, traditional cost models often beat LCMs, guiding future work. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 7233
Venue: SIGMOD
Year: 2025
Pagerank: 4.9627485e-05
Overall Rank: 6,685 | 53.50%
DOI: 10.1145/3725309

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 9 of 9 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
9,981	Survivorship Bias in Industrial Database Workloads	2026	CIDR	4.1945683e-05
10,203	Reqo: A Comprehensive Learning-Based Cost Model for Robust and Explainable Query Optimization	2026	SIGMOD	4.1945683e-05
10,217	This is Going to Sound Crazy, But What If We Used Large Language Models to Boost Automatic Database Tuning Algorithms By Leveraging Prior History? We Will Find Better Configurations More Quickly Than Retraining From Scratch!	2026	SIGMOD	4.1945683e-05
10,227	Sample-based Distinct Cardinality Estimation for Multiple Attributes in Multi-Dataset Queries	2026	VLDB	4.1945683e-05
10,271	OBELISK: Efficient Offline Query Planning with Bayesian Optimization-Informed Language Model Reasoning	2026	VLDB	4.1945683e-05
10,293	Vodka: Rethink Benchmarking Philosophy in HTAP Systems	2026	VLDB	4.1945683e-05
10,310	SafeLoad: Efficient Admission Control Framework for Identifying Memory-Overloading Queries in Cloud Data Warehouses	2026	VLDB	4.1945683e-05
10,795	Opening The Black-Box: Explaining Learned Cost Models For Databases	2025	VLDB	4.1945683e-05
10,840	Learned Cost Models for Query Optimization: From Batch to Streaming Systems	2025	VLDB	4.1945683e-05

Outgoing Citations (Sorted by Pagerank)

Showing 28 of 28 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
1	Access Path Selection in a Relational Database Management System	1979	SIGMOD	0.0040449103
71	How Good Are Query Optimizers, Really?	2016	VLDB	0.00059038975
204	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00034784455
608	DeepDB: Learn from Data, not from Queries!	2020	VLDB	0.00019235898
640	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00018759152
718	Performance Prediction for Concurrent Database Workloads	2011	SIGMOD	0.0001763106
758	Deep Unsupervised Cardinality Estimation	2020	VLDB	0.0001706608
806	An End-to-End Learning-based Cost Estimator	2020	VLDB	0.00016434274
884	Plan-Structured Deep Neural Network Models for Query Performance Prediction	2019	VLDB	0.00015654004
910	NeuroCard: One Cardinality Estimator for All Tables	2021	VLDB	0.00015423056
1,703	Are We Ready For Learned Cardinality Estimation?	2021	VLDB	0.00010836769
2,121	Balsa: Learning a Query Optimizer Without Expert Demonstrations	2022	SIGMOD	9.5017232e-05
3,169	QueryFormer: A Tree Transformer Model for Query Plan Representation	2022	VLDB	7.4498425e-05
3,178	Why TPC Is Not Enough: An Analysis of the Amazon Redshift Fleet	2024	VLDB	7.4325992e-05
3,266	Learned Cardinality Estimation: An In-depth Study	2022	SIGMOD	7.3074684e-05
3,348	Lero: A Learning-to-Rank Query Optimizer	2023	VLDB	7.1904529e-05
3,449	Learned Cardinality Estimation: A Design Space Exploration and A Comparative Evaluation	2022	VLDB	7.0824319e-05
3,580	Query Performance Prediction for Concurrent Queries using Graph Embedding	2020	VLDB	6.9500996e-05
3,828	Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction	2022	VLDB	6.7208524e-05
4,717	Cloud Analytics Benchmark	2023	VLDB	5.9751539e-05
5,334	LEON: A New Framework for ML-Aided Query Optimization	2023	VLDB	5.5649836e-05
5,423	Kepler: Robust Learning for Faster Parametric Query Optimization	2023	SIGMOD	5.5130233e-05
6,328	A Comparative Study and Component Analysis of Query Plan Representation Techniques in ML4DB Studies	2024	VLDB	5.1082882e-05
6,368	Pre-training Summarization Models of Structured Datasets for Cardinality Estimation	2022	VLDB	5.0937722e-05
6,383	Sample-Efficient Cardinality Estimation Using Geometric Deep Learning	2024	VLDB	5.0884322e-05
6,775	A Unified Transferable Model for ML-Enhanced DBMS	2022	CIDR	4.9299192e-05
7,008	Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective	2024	VLDB	4.8643538e-05
7,753	Rethinking Learned Cost Models: Why Start from Scratch?	2023	SIGMOD	4.660151e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
1,703	Are We Ready For Learned Cardinality Estimation?	2021	VLDB	0.00010836769
806	An End-to-End Learning-based Cost Estimator	2020	VLDB	0.00016434274
3,954	Efficiently Approximating Selectivity Functions using Low Overhead Regression Models	2020	VLDB	6.5926838e-05
9,120	Deep Query Optimization	2019	SIGMOD	4.392741e-05
7,008	Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective	2024	VLDB	4.8643538e-05
7,753	Rethinking Learned Cost Models: Why Start from Scratch?	2023	SIGMOD	4.660151e-05
5,861	Machine Learning for Databases	2021	VLDB	5.298883e-05
3,828	Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction	2022	VLDB	6.7208524e-05
3,727	Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection	2022	VLDB	6.8141709e-05
10,840	Learned Cost Models for Query Optimization: From Batch to Streaming Systems	2025	VLDB	4.1945683e-05