E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model
Summary: E2ETune frames DB knob tuning as seq2seq generation: fine-tunes a generative language model on synthetic workload→promising-configuration pairs produced by a novel data-generation pipeline. Produces one-shot, out-of-the-box config recommendations that match SOTA with far fewer workload replays. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Xinmei Huang (Renmin University of China)
- 2. Haoyang Li (Renmin University of China)
- 3. Jing Zhang (Renmin University of China)
- 4. Xinxin Zhao (Renmin University of China)
- 5. Zhiming Yao (Renmin University of China)
- 6. Yiyan Li (Renmin University of China)
- 7. Tieying Zhang (ByteDance)
- 8. Jianjun Chen (ByteDance)
- 9. Hong Chen (Renmin University of China)
- 10. Cuiping Li (Renmin University of China)
BibTeX Citation
@article{huang_vldb25,
title = {{E2ETune: End-to-End Knob Tuning via Fine-tuned Generative Language Model}},
author = {Huang, Xinmei and Li, Haoyang and Zhang, Jing and Zhao, Xinxin and Yao, Zhiming and Li, Yiyan and Zhang, Tieying and Chen, Jianjun and Chen, Hong and Li, Cuiping},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {13},
pages = {5540--5554},
doi = {10.14778/3773731.3773732},
url = {https://doi.org/10.14778/3773731.3773732},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 35 of 35 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next