A Unified Transferable Model for ML-Enhanced DBMS
Summary: MTMLF: unified transferable ML for DBMS, using multi-task training to capture cross-task signals and pretrain–fine-tune to distill meta-knowledge across databases, eliminating expensive per-DB retraining and large new-data needs. Demonstrated for query optimization. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Ziniu Wu (Massachusetts Institute of Technology)
- 2. Pei Yu (Alibaba; University of Science and Technology Beijing)
- 3. Peilun Yang (Alibaba; University of Technology Sydney)
- 4. Rong Zhu (Alibaba)
- 5. Yuxing Han (Alibaba)
- 6. Yaliang Li (Alibaba)
- 7. Defu Lian (University of Science and Technology Beijing)
- 8. Kai Zeng (Alibaba)
- 9. Jingren Zhou (Alibaba)
BibTeX Citation
@inproceedings{wu_cidr22,
address = {Amsterdam, Netherlands},
series = {{CIDR} '22},
title = {{A Unified Transferable Model for ML-Enhanced DBMS}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Wu, Ziniu and Yu, Pei and Yang, Peilun and Zhu, Rong and Han, Yuxing and Li, Yaliang and Lian, Defu and Zeng, Kai and Zhou, Jingren},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 13 of 13 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 22 of 22 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 | 11,481 | Demonstration of OpenDBML, a Framework for Democratizing In-Database Machine Learning | 2023 | VLDB |
| 2 | 334 | An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning | 2019 | SIGMOD |
| 3 | 2,786 | DB4ML – An In-Memory Database Kernel with Machine Learning Support | 2020 | SIGMOD |
| 4 | 9,536 | Database Gyms | 2023 | CIDR |
| 5 | 6,600 | A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning | 2023 | SIGMOD |
| 6 | 9,962 | Structure-Aware Machine Learning over Multi-Relational Databases | 2021 | SIGMOD |
| 7 | 4,468 | One Model to Rule them All: Towards Zero-Shot Learning for Databases | 2022 | CIDR |
| 8 | 8,854 | Towards Foundation Database Models | 2025 | CIDR |
| 9 | 5,340 | Machine Learning for Databases | 2021 | VLDB |
| 10 | 3,614 | Cloudy with High Chance of DBMS: A 10-year Prediction for Enterprise-Grade ML | 2020 | CIDR |