AdaNDV: Adaptive Number of Distinct Value Estimation via Learning to Select and Fuse Estimators
Summary: AdaNDV learns to adaptively select complementary NDV estimators by classifying over- vs under-estimators and picking from each category for error correction. It then predicts fusion weights to combine selected estimators, improving accuracy at large scale versus direct NDV learners. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Xianghong Xu (ByteDance)
- 2. Tieying Zhang (ByteDance)
- 3. Xiao He (ByteDance)
- 4. Haoyang Li (ByteDance)
- 5. Rong Kang (ByteDance)
- 6. Shuai Wang (ByteDance)
- 7. Linhui Xu (ByteDance)
- 8. Zhimin Liang (ByteDance)
- 9. Shangyu Luo (ByteDance)
- 10. Lei Zhang (ByteDance)
- 11. Jianjun Chen (ByteDance)
BibTeX Citation
@article{xu_vldb25,
title = {{AdaNDV: Adaptive Number of Distinct Value Estimation via Learning to Select and Fuse Estimators}},
author = {Xu, Xianghong and Zhang, Tieying and He, Xiao and Li, Haoyang and Kang, Rong and Wang, Shuai and Xu, Linhui and Liang, Zhimin and Luo, Shangyu and Zhang, Lei and Chen, Jianjun},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {4},
pages = {1104--1117},
doi = {10.14778/3717755.3717769},
url = {https://doi.org/10.14778/3717755.3717769},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,079 | VIDEX: A Disaggregated and Extensible Virtual Index for the Cloud and AI Era | 2025 | VLDB | 5.158939e-05 |
| 10,774 | PLM4NDV: Minimizing Data Access for Number of Distinct Values Estimation with Pre-trained Language Models | 2025 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 13 of 13 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 | 1,573 | Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries | 2020 | SIGMOD |
| 2 | 10,851 | ACE: A Cardinality Estimator for Set-Valued Queries | 2025 | VLDB |
| 3 | 2,723 | Learned Cardinality Estimation: A Design Space Exploration and A Comparative Evaluation | 2022 | VLDB |
| 4 | 222 | Adaptive Selectivity Estimation Using Query Feedback | 1994 | SIGMOD |
| 5 | 288 | Towards Estimation Error Guarantees for Distinct Values | 2000 | PODS |
| 6 | 9,491 | CEDA: Learned Cardinality Estimation with Domain Adaptation | 2023 | VLDB |
| 7 | 8,124 | Consistent and Flexible Selectivity Estimation for High-Dimensional Data | 2021 | SIGMOD |
| 8 | 8,850 | Learning-based Property Estimation with Polynomials | 2024 | SIGMOD |
| 9 | 10,774 | PLM4NDV: Minimizing Data Access for Number of Distinct Values Estimation with Pre-trained Language Models | 2025 | SIGMOD |
| 10 | 7,290 | Learning to be a Statistician: Learned Estimator for Number of Distinct Values | 2022 | VLDB |