DBScholar

Back to papers

Are We Ready For Learned Cardinality Estimation?

Summary: Assess readiness of learned cardinality estimators for production; static workloads yield gains, but training/inference costs are high. Dynamic updates hurt accuracy; sensitivity to correlation, skew, and domain shifts; emphasizes cost control and trustworthiness. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
12539
Venue
VLDB
Year
2021
Pagerank
0.00012369764
Overall Rank
1,061 | 92.73%
DOI
10.14778/3461535.3461552

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{wang_vldb21,
        title = {{Are We Ready For Learned Cardinality Estimation?}},
        author = {Wang, Xiaoying and Qu, Changbo and Wu, Weiyuan and Wang, Jiannan and Zhou, Qingqing},
        journal = {PVLDB},
        series = {{VLDB} '21},
        volume = {14},
        number = {9},
        pages = {1640--1654},
        doi = {10.14778/3461535.3461552},
        url = {https://doi.org/10.14778/3461535.3461552},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 10 of 60 citing papers.

Previous Page 2 / 2 Next

Outgoing Citations (Sorted by Pagerank)

Showing 2 of 52 cited papers.

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

Rank Cited Paper Year Venue Pagerank
4,277 Adaptive Statistics in Oracle 12c 2017 VLDB 6.7873816e-05
4,789 Learned Approximate Query Processing: Make it Light, Accurate and Fast 2021 CIDR 6.5072039e-05
Previous Page 2 / 2 Next

Semantically Similar Papers