Learned Cost Models for Query Optimization: From Batch to Streaming Systems

Summary: Unified overview of learned cost models (LCMs) for batch and streaming query optimization, contrasting input representations, model architectures, and optimizer integration. Emphasizes streaming-specific challenges—latency, non‑stationarity, continuous learning—and deployment tradeoffs. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: h06eb12ace069652d
Venue: VLDB
Year: 2025
Pagerank: 4.9793485e-05
Overall Rank: 11,425 | 23.19%
DOI: 10.14778/3750601.3750699

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Roman Heinrich (German National Research Center for Information Technology; Technical University of Darmstadt)
2. Xiao Li (IT University of Copenhagen)
3. Manisha Luthra (German National Research Center for Information Technology; Technical University of Darmstadt)
4. Zoi Kaoudi (IT University of Copenhagen)

BibTeX Citation

@article{heinrich_vldb25,
        title = {{Learned Cost Models for Query Optimization: From Batch to Streaming Systems}},
        author = {Heinrich, Roman and Li, Xiao and Luthra, Manisha and Kaoudi, Zoi},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {12},
        pages = {5482--5487},
        doi = {10.14778/3750601.3750699},
        url = {https://doi.org/10.14778/3750601.3750699},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

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	0.0023947656
15	How Good Are Query Optimizers, Really?	2016	VLDB	0.00061066921
85	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00035864347
145	Neo: A Learned Query Optimizer	2019	VLDB	0.0002908188
362	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00019989474
386	Preventing Bad Plans by Bounding the Impact of Cardinality Estimation Errors	2009	VLDB	0.00019444411
461	An End-to-End Learning-based Cost Estimator	2020	VLDB	0.00017829982
560	Plan-Structured Deep Neural Network Models for Query Performance Prediction	2019	VLDB	0.00016403151
1,199	Balsa: Learning a Query Optimizer Without Expert Demonstrations	2022	SIGMOD	0.00011563985
2,210	Lero: A Learning-to-Rank Query Optimizer	2023	VLDB	8.8257742e-05
2,250	QueryFormer: A Tree Transformer Model for Query Plan Representation	2022	VLDB	8.7533306e-05
2,690	Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection	2022	VLDB	8.1258173e-05
2,885	Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction	2022	VLDB	7.9094988e-05
2,908	AI Meets Database: AI4DB and DB4AI	2021	SIGMOD	7.8742664e-05
3,487	LOGER: A Learned Optimizer towards Generating Efficient and Robust Query Execution Plans	2023	VLDB	7.263041e-05
3,563	Auto-WLM: Machine Learning Enhanced Workload Management in Amazon Redshift	2023	SIGMOD	7.2042148e-05
4,258	LEON: A New Framework for ML-Aided Query Optimization	2023	VLDB	6.6994722e-05
4,741	Machine Learning for Databases	2021	VLDB	6.4410027e-05
5,214	Stage: Query Execution Time Prediction in Amazon Redshift	2024	SIGMOD	6.2248104e-05
5,683	How Good are Learned Cost Models, Really? Insights from Query Optimization Tasks	2025	SIGMOD	6.0392183e-05
6,141	Expand your Training Limits! Generating Training Data for ML-based Data Management	2021	SIGMOD	5.8733296e-05
7,033	Rethinking Learned Cost Models: Why Start from Scratch?	2023	SIGMOD	5.6168499e-05
7,315	Model-Free Control for Distributed Stream Data Processing using Deep Reinforcement Learning	2018	VLDB	5.554799e-05
7,460	T3: Accurate and Fast Performance Prediction for Relational Database Systems With Compiled Decision Trees	2025	SIGMOD	5.5215755e-05
9,200	Dalton: Learned Partitioning for Distributed Data Streams	2023	VLDB	5.2084806e-05
9,533	Farm Your ML-based Query Optimizer's Food! - Human-Guided Training Data Generation -	2022	CIDR	5.1636858e-05
9,800	Apache Wayang in Action: Enabling Data Systems Integration via a Unified Data Analytics Framework	2025	SIGMOD	5.1257999e-05
11,388	Opening The Black-Box: Explaining Learned Cost Models For Databases	2025	VLDB	4.9793485e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	5,110	Steering Query Optimizers: A Practical Take on Big Data Workloads	2021	SIGMOD
2	4,741	Machine Learning for Databases	2021	VLDB
3	461	An End-to-End Learning-based Cost Estimator	2020	VLDB
4	8,879	Spatial Query Optimization With Learning	2024	VLDB
5	5,865	Modeling Shifting Workloads for Learned Database Systems	2024	SIGMOD
6	11,388	Opening The Black-Box: Explaining Learned Cost Models For Databases	2025	VLDB
7	2,834	Cost Models for Big Data Query Processing: Learning, Retrofitting, and Our Findings	2020	SIGMOD
8	7,033	Rethinking Learned Cost Models: Why Start from Scratch?	2023	SIGMOD
9	2,885	Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction	2022	VLDB
10	5,683	How Good are Learned Cost Models, Really? Insights from Query Optimization Tasks	2025	SIGMOD