Back to papers
Flow-Loss: Learning Cardinality Estimates That Matter
Summary: Flow-Loss, a cardinality loss that directly optimizes the optimizer’s cost via a flow-routing plan graph. On the Cardinality Estimation Benchmark, it reduces plan costs and 99th-percentile runtimes on unseen templates, achieving 4–8x gains and better generalization than Q-Error models.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 12383
- Venue
- VLDB
- Year
- 2021
- Pagerank
- 8.1282042e-05
- Overall Rank
- 2,781 | 80.68%
- DOI
-
10.14778/3476249.3476259
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 3 of 53 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.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 71 |
How Good Are Query Optimizers, Really? |
2016 |
VLDB |
0.00059446482 |
| 141 |
Selectivity Estimation Without the Attribute Value Independence Assumption |
1997 |
VLDB |
0.00041819767 |
| 203 |
Learned Cardinalities: Estimating Correlated Joins with Deep Learning |
2019 |
CIDR |
0.00034868567 |
| 223 |
Wavelet-Based Histograms for Selectivity Estimation |
1998 |
SIGMOD |
0.00032829841 |
| 329 |
Neo: A Learned Query Optimizer |
2019 |
VLDB |
0.00027301488 |
| 373 |
Selectivity Estimation using Probabilistic Models |
2001 |
SIGMOD |
0.00025354685 |
| 512 |
STHoles: A Multidimensional Workload-Aware Histogram |
2001 |
SIGMOD |
0.00021385343 |
| 606 |
DeepDB: Learn from Data, not from Queries! |
2020 |
VLDB |
0.00019251186 |
| 627 |
Preventing Bad Plans by Bounding the Impact of Cardinality Estimation Errors |
2009 |
VLDB |
0.00018959896 |
| 752 |
Deep Unsupervised Cardinality Estimation |
2020 |
VLDB |
0.00017138049 |
| 804 |
An End-to-End Learning-based Cost Estimator |
2020 |
VLDB |
0.0001643674 |
| 905 |
NeuroCard: One Cardinality Estimator for All Tables |
2021 |
VLDB |
0.00015423174 |
| 941 |
Wander Join: Online Aggregation via Random Walks |
2016 |
SIGMOD |
0.00015147831 |
| 1,104 |
Cardinality Estimation Done Right: Index-Based Join Sampling |
2017 |
CIDR |
0.0001398479 |
| 1,239 |
Selectivity Estimation for Range Predicates using Lightweight Models |
2019 |
VLDB |
0.00013091459 |
| 1,372 |
Random Sampling over Joins Revisited |
2018 |
SIGMOD |
0.0001233325 |
| 1,699 |
Are We Ready For Learned Cardinality Estimation? |
2021 |
VLDB |
0.00010848882 |
| 1,727 |
QuickSel: Quick Selectivity Learning with Mixture Models |
2020 |
SIGMOD |
0.00010731889 |
| 2,080 |
Towards a Learning Optimizer for Shared Clouds |
2019 |
VLDB |
9.5954034e-05 |
| 2,143 |
Pessimistic Cardinality Estimation: Tighter Upper Bounds for Intermediate Join Cardinalities |
2019 |
SIGMOD |
9.4437798e-05 |
| 2,222 |
SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning |
2019 |
SIGMOD |
9.2598438e-05 |
| 2,364 |
Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries |
2020 |
SIGMOD |
8.955077e-05 |
| 2,971 |
Estimating Join Selectivities using Bandwidth-Optimized Kernel Density Models |
2017 |
VLDB |
7.7935535e-05 |
| 3,516 |
Accurate Summary-based Cardinality Estimation Through the Lens of Cardinality Estimation Graphs |
2022 |
VLDB |
7.018912e-05 |
| 3,658 |
Towards a Hands-Free Query Optimizer through Deep Learning |
2019 |
CIDR |
6.8700949e-05 |
| 3,725 |
Estimating Cardinalities with Deep Sketches |
2019 |
SIGMOD |
6.8117015e-05 |
| 3,955 |
Efficiently Approximating Selectivity Functions using Low Overhead Regression Models |
2020 |
VLDB |
6.5895015e-05 |
| 4,526 |
Simplicity Done Right for Join Ordering |
2021 |
CIDR |
6.1079584e-05 |
Semantically Similar Papers