Turbo-Charging SPJ Query Plans with Learned Physical Join Operator Selections

Summary: TONIC adds learning-based, cardinality-free operator selection to SPJ optimizers, revising join choices along paths via feedback. It introduces QEP-S to capture and reuse optimal operator decisions, delivering up to 2.8x speedups on benchmarks. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: hda79ae3959c14799
Venue: VLDB
Year: 2022
Pagerank: 5.0412674e-05
Overall Rank: 10,249 | 31.30%
DOI: 10.14778/3551793.3551825
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

1. Axel Hertzschuch (Technical University of Dresden)
2. Claudio Hartmann (Technical University of Dresden)
3. Dirk Habich (Technical University of Dresden)
4. Wolfgang Lehner (Technical University of Dresden)

BibTeX Citation

@article{hertzschuch_vldb22,
        title = {{Turbo-Charging SPJ Query Plans with Learned Physical Join Operator Selections}},
        author = {Hertzschuch, Axel and Hartmann, Claudio and Habich, Dirk and Lehner, Wolfgang},
        journal = {PVLDB},
        series = {{VLDB} '22},
        volume = {15},
        number = {11},
        pages = {2706--2718},
        doi = {10.14778/3551793.3551825},
        url = {https://doi.org/10.14778/3551793.3551825},
        year = {2022}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
5,245	FASTgres: Making Learned Query Optimizer Hinting Effective	2023	VLDB	6.1995935e-05
6,840	ASM: Harmonizing Autoregressive Model, Sampling, and Multi-dimensional Statistics Merging for Cardinality Estimation	2024	SIGMOD	5.6513231e-05
10,370	An Elephant Under The Microscope: Analyzing The Interaction Of Optimizer Components In PostgreSQL	2025	SIGMOD	5.0010514e-05

Outgoing Citations (Sorted by Pagerank)

Showing 25 of 25 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
15	How Good Are Query Optimizers, Really?	2016	VLDB	0.00061463175
53	Eddies: Continuously Adaptive Query Processing	2000	SIGMOD	0.00040739114
84	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00035920657
98	LEO - DB2's LEarning Optimizer	2001	VLDB	0.00034050614
142	Neo: A Learned Query Optimizer	2019	VLDB	0.00029114937
171	Wavelet-Based Histograms for Selectivity Estimation	1998	SIGMOD	0.00027063233
254	The History of Histograms (abridged)	2003	VLDB	0.00022999992
259	An Overview of Query Optimization in Relational Systems	1998	PODS	0.00022881075
311	Approximate Query Processing Using Wavelets	2000	VLDB	0.00021315058
320	DeepDB: Learn from Data, not from Queries!	2020	VLDB	0.00021128745
355	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00020146245
372	STHoles: A Multidimensional Workload-Aware Histogram	2001	SIGMOD	0.00019768921
508	NeuroCard: One Cardinality Estimator for All Tables	2021	VLDB	0.00017108973
1,213	A Seven-Dimensional Analysis of Hashing Methods and its Implications on Query Processing	2016	VLDB	0.00011492443
1,444	Pessimistic Cardinality Estimation: Tighter Upper Bounds for Intermediate Join Cardinalities	2019	SIGMOD	0.00010616242
1,740	Flow-Loss: Learning Cardinality Estimates That Matter	2021	VLDB	9.7289523e-05
1,808	An Adaptive Hash Join Algorithm for Multiuser Environments	1990	VLDB	9.5852314e-05
2,438	Cardinality Estimation Using Sample Views with Quality Assurance	2007	SIGMOD	8.4532693e-05
2,888	Query Optimizers: Time to Rethink the Contract?	2009	SIGMOD	7.8895201e-05
3,282	Estimating Cardinalities with Deep Sketches	2019	SIGMOD	7.4491295e-05
3,995	Simplicity Done Right for Join Ordering	2021	CIDR	6.8530469e-05
4,069	Adaptive Query Processing in the Looking Glass	2005	CIDR	6.8080574e-05
5,029	COMPASS: Online Sketch-based Query Optimization for In-Memory Databases	2021	SIGMOD	6.2952031e-05
8,363	alpha to omega: The Greek Alphabet of Sampling	2020	CIDR	5.3305234e-05
9,667	Small Selectivities Matter: Lifting the Burden of Empty Samples	2021	SIGMOD	5.1278365e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,564	Sub-optimal Join Order Identification with L1-error	2024	SIGMOD
2	1,185	Adaptive Optimization of Very Large Join Queries	2018	SIGMOD
3	3,995	Simplicity Done Right for Join Ordering	2021	CIDR
4	4,435	Estimating Compilation Time of a Query Optimizer	2003	SIGMOD
5	8,188	Efficient Query Re-optimization with Judicious Subquery Selections	2023	SIGMOD
6	3,807	Query Simplification: Graceful Degradation for Join-Order Optimization	2009	SIGMOD
7	7,387	Weighted Distinct Sampling: Cardinality Estimation for SPJ Queries	2021	SIGMOD
8	3,050	Configuration-Parametric Query Optimization for Physical Design Tuning	2008	SIGMOD
9	15	How Good Are Query Optimizers, Really?	2016	VLDB
10	8,389	GenJoin: Conditional Generative Plan-to-Plan Query Optimizer that Learns from Subplan Hints	2026	SIGMOD