An Efficient Transfer Learning Based Configuration Adviser for Database Tuning
Summary: OpAdviser transfers knowledge across tuning tasks to identify effective knob regions and adaptively construct compact search spaces. A pairwise model selects optimizers per task/iteration, yielding 9.2% higher throughput and ~3.4× fewer workload runs than state-of-the-art systems. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xinyi Zhang (Peking University)
- 2. Hong Wu (Alibaba)
- 3. Yang Li (Peking University)
- 4. Zhengju Tang (Peking University)
- 5. Jian Tan (Alibaba)
- 6. Feifei Li (Alibaba)
- 7. Bin Cui (Peking University)
BibTeX Citation
@article{zhang_vldb24,
title = {{An Efficient Transfer Learning Based Configuration Adviser for Database Tuning}},
author = {Zhang, Xinyi and Wu, Hong and Li, Yang and Tang, Zhengju and Tan, Jian and Li, Feifei and Cui, Bin},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {3},
pages = {539--552},
doi = {10.14778/3632093.3632114},
url = {https://doi.org/10.14778/3632093.3632114},
year = {2024}
}
Incoming Citations (Sorted by Pagerank)
Showing 14 of 14 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 26 of 26 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next