LIMAO: A Framework for Lifelong Modular Learned Query Optimization

Summary: LIMAO: a lifelong, modular framework that equips learned query optimizers with attention-based neural composition and continual learning to retain cost-prediction knowledge across evolving workloads. Engine-agnostic plug-in improves plan stability and performance (large runtime reductions vs. baselines and Postgres) and mitigates catastrophic forgetting. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: hf670c5f1dfeb1e04
Venue: VLDB
Year: 2025
Pagerank: 5.2790784e-05
Overall Rank: 8,657 | 41.98%
DOI: 10.14778/3749646.3749712
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Qihan Zhang (University of Southern California)
2. Shaolin Xie (University of Southern California)
3. Ibrahim Sabek (University of Southern California)

BibTeX Citation

@article{zhang_vldb25,
        title = {{LIMAO: A Framework for Lifelong Modular Learned Query Optimization}},
        author = {Zhang, Qihan and Xie, Shaolin and Sabek, Ibrahim},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {11},
        pages = {4546--4559},
        doi = {10.14778/3749646.3749712},
        url = {https://doi.org/10.14778/3749646.3749712},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,420	Rethinking Query Optimization for Multi-Agent Systems	2027	VLDB	4.9605343e-05
10,705	Divo: Learning a Stable and Effective Query Optimizer with a Diverse Workload	2026	SIGMOD	4.9605343e-05
10,812	OBELISK: Efficient Offline Query Planning with Bayesian Optimization-Informed Language Model Reasoning	2026	VLDB	4.9605343e-05

Outgoing Citations (Sorted by Pagerank)

Showing 35 of 35 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	0.0023948467
15	How Good Are Query Optimizers, Really?	2016	VLDB	0.00061463175
40	The Case for Learned Index Structures	2018	SIGMOD	0.00046249672
84	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00035920657
142	Neo: A Learned Query Optimizer	2019	VLDB	0.00029114937
355	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00020146245
405	Deep Unsupervised Cardinality Estimation	2020	VLDB	0.00019020138
427	ALEX: An Updatable Adaptive Learned Index	2020	SIGMOD	0.00018429918
453	An End-to-End Learning-based Cost Estimator	2020	VLDB	0.0001801482
508	NeuroCard: One Cardinality Estimator for All Tables	2021	VLDB	0.00017108973
545	Plan-Structured Deep Neural Network Models for Query Performance Prediction	2019	VLDB	0.0001657599
1,061	Lightweight Graphical Models for Selectivity Estimation Without Independence Assumptions	2011	VLDB	0.00012207625
1,175	Balsa: Learning a Query Optimizer Without Expert Demonstrations	2022	SIGMOD	0.00011630532
1,238	DB-BERT: A Database Tuning Tool that "Reads the Manual"	2022	SIGMOD	0.00011375179
1,740	Flow-Loss: Learning Cardinality Estimates That Matter	2021	VLDB	9.7289523e-05
2,009	FLAT: Fast, Lightweight and Accurate Method for Cardinality Estimation	2021	VLDB	9.1813272e-05
2,190	Lero: A Learning-to-Rank Query Optimizer	2023	VLDB	8.8848923e-05
2,227	GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization	2024	VLDB	8.7924681e-05
2,348	Learned Cardinality Estimation: An In-depth Study	2022	SIGMOD	8.5910072e-05
2,523	Learned Cardinality Estimation: A Design Space Exploration and A Comparative Evaluation	2022	VLDB	8.3316032e-05
2,619	Zero-Shot Cost Models for Out-of-the-box Learned Cost Prediction	2022	VLDB	8.1985665e-05
2,696	Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection	2022	VLDB	8.1068354e-05
3,060	A Unified Deep Model of Learning from both Data and Queries for Cardinality Estimation	2021	SIGMOD	7.6828463e-05
3,212	Efficiently Approximating Selectivity Functions using Low Overhead Regression Models	2020	VLDB	7.5145409e-05
3,269	Robust Query Driven Cardinality Estimation under Changing Workloads	2023	VLDB	7.463682e-05
3,481	LOGER: A Learned Optimizer towards Generating Efficient and Robust Query Execution Plans	2023	VLDB	7.2463722e-05
4,202	Kepler: Robust Learning for Faster Parametric Query Optimization	2023	SIGMOD	6.7258607e-05
4,247	LEON: A New Framework for ML-Aided Query Optimization	2023	VLDB	6.6920059e-05
4,315	ALECE: An Attention-based Learned Cardinality Estimator for SPJ Queries on Dynamic Workloads	2024	VLDB	6.6545412e-05
4,459	Warper: Efficiently Adapting Learned Cardinality Estimators to Data and Workload Drifts	2022	SIGMOD	6.5757572e-05
4,549	One Model to Rule them All: Towards Zero-Shot Learning for Databases	2022	CIDR	6.5328866e-05
4,797	LSched: A Workload-Aware Learned Query Scheduler for Analytical Database Systems	2022	SIGMOD	6.3978116e-05
5,453	Eraser: Eliminating Performance Regression on Learned Query Optimizer	2024	VLDB	6.1077838e-05
5,794	Lemo: A Cache-Enhanced Learned Optimizer for Concurrent Queries	2023	SIGMOD	5.9759435e-05
5,854	Modeling Shifting Workloads for Learned Database Systems	2024	SIGMOD	5.9520525e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,392	E-LQO: A Comprehensive Energy Evaluation Framework for Learned Query Optimization	2027	SIGMOD
2	2,673	A Layered Aggregate Engine for Analytics Workloads	2019	SIGMOD
3	10,769	LIO: A lightweight and interpretable query optimizer based on an evolutionary forest	2026	VLDB
4	142	Neo: A Learned Query Optimizer	2019	VLDB
5	11,907	DeepO: A Learned Query Optimizer	2022	SIGMOD
6	6,109	Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective	2024	VLDB
7	2,190	Lero: A Learning-to-Rank Query Optimizer	2023	VLDB
8	6,584	Can Large Language Models Be Query Optimizer for Relational Databases?	2026	SIGMOD
9	5,794	Lemo: A Cache-Enhanced Learned Optimizer for Concurrent Queries	2023	SIGMOD
10	9,662	Low Rank Learning for Offline Query Optimization	2025	SIGMOD