Flow-Loss: Learning Cardinality Estimates That Matter
Summary: Flow-Loss trains cardinality estimators against optimizer plan costs via a flow-routing formulation over plan graphs, rather than average Q-Error. On the 16K-query CEB benchmark, it yields better runtimes and markedly stronger generalization to unseen templates despite worse estimation accuracy. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Parimarjan Negi (Massachusetts Institute of Technology)
- 2. Ryan Marcus (Intel; Massachusetts Institute of Technology)
- 3. Andreas Kipf (Massachusetts Institute of Technology)
- 4. Hongzi Mao (Massachusetts Institute of Technology)
- 5. Nesime Tatbul (Intel; Massachusetts Institute of Technology)
- 6. Tim Kraska (Massachusetts Institute of Technology)
- 7. Mohammad Alizadeh (Massachusetts Institute of Technology)
BibTeX Citation
@article{negi_vldb21,
title = {{Flow-Loss: Learning Cardinality Estimates That Matter}},
author = {Negi, Parimarjan and Marcus, Ryan and Kipf, Andreas and Mao, Hongzi and Tatbul, Nesime and Kraska, Tim and Alizadeh, Mohammad},
journal = {PVLDB},
series = {{VLDB} '21},
volume = {14},
number = {11},
pages = {2019--2032},
doi = {10.14778/3476249.3476259},
url = {https://doi.org/10.14778/3476249.3476259},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 50 of 55 citing papers.
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.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,723 | Learned Cardinality Estimation: A Design Space Exploration and A Comparative Evaluation | 2022 | VLDB |
| 2 | 3,338 | Robust Query Driven Cardinality Estimation under Changing Workloads | 2023 | VLDB |
| 3 | 9,867 | SPACE: Cardinality Estimation for Path Queries Using Cardinality-Aware Sequence-based Learning | 2025 | SIGMOD |
| 4 | 6,543 | Speeding Up End-to-end Query Execution via Learning-based Progressive Cardinality Estimation | 2023 | SIGMOD |
| 5 | 465 | An End-to-End Learning-based Cost Estimator | 2020 | VLDB |
| 6 | 11,160 | Sub-optimal Join Order Identification with L1-error | 2024 | SIGMOD |
| 7 | 388 | Preventing Bad Plans by Bounding the Impact of Cardinality Estimation Errors | 2009 | VLDB |
| 8 | 1,061 | Are We Ready For Learned Cardinality Estimation? | 2021 | VLDB |
| 9 | 1,468 | Towards a Learning Optimizer for Shared Clouds | 2019 | VLDB |
| 10 | 1,122 | Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation | 2022 | VLDB |