DBScholar

Back to papers

Learning Table Access Cardinalities with LEO

Summary: LEO uses a feedback loop to learn from executions, repairing cardinalities and predicate selectivities to improve estimates. It generalizes to similar queries, detects cardinality errors across operators, piggybacks on prior runs with negligible overhead. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
hed2efb970b00e3c7
Venue
SIGMOD
Year
2002
Pagerank
5.3614914e-05
Overall Rank
8,288 | 44.28%
DOI
10.1145/564691.564766

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{markl_sigmod02,
        title = {{Learning Table Access Cardinalities with LEO}},
        author = {Markl, Volker and Lohman, Guy},
        series = {{SIGMOD} '02},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/564691.564766},
        url = {https://dl.acm.org/doi/10.1145/564691.564766},
        year = {2002}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank Citing Paper Year Venue Pagerank
2,433 Cardinality Estimation Using Sample Views with Quality Assurance 2007 SIGMOD 8.4766785e-05
6,141 Expand your Training Limits! Generating Training Data for ML-based Data Management 2021 SIGMOD 5.8733296e-05
12,777 Visualizing the robustness of query execution 2009 CIDR 4.9793485e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 1 of 1 cited papers.

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

Rank Cited Paper Year Venue Pagerank
98 LEO - DB2's LEarning Optimizer 2001 VLDB 0.00034106982
Previous Page 1 / 1 Next

Semantically Similar Papers