TATA: An Efficient Framework for Task Transfer in Query Plan Representation
Summary: TATA: a task-transfer framework for query-plan representations that augments pretraining with a self-supervised plan decoder to produce robust, task-agnostic embeddings. Mitigates small-label and distribution-shift issues by synthesizing realistic pseudo-labeled plans using DB domain knowledge, yielding up to 5x reduction in dataset collection cost and working across multiple plan encoders. (summarized by gpt-5-mini on Mar 13 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yue Zhao (Nanyang Technological University)
- 2. Songsong Mo (Nanyang Technological University)
- 3. Gao Cong (Nanyang Technological University)
BibTeX Citation
@article{zhao_vldb26,
title = {{TATA: An Efficient Framework for Task Transfer in Query Plan Representation}},
author = {Zhao, Yue and Mo, Songsong and Cong, Gao},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {3},
pages = {413--425},
doi = {10.14778/3778092.3778102},
url = {https://doi.org/10.14778/3778092.3778102},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 11,008 | Towards Industrial-Scale Parametric Query Optimization | 2026 | VLDB | 4.9605343e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 31 of 31 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 | 545 | Plan-Structured Deep Neural Network Models for Query Performance Prediction | 2019 | VLDB |
| 2 | 4,720 | PreQR: Pre-training Representation for SQL Understanding | 2022 | SIGMOD |
| 3 | 4,765 | Machine Learning for Databases | 2021 | VLDB |
| 4 | 4,549 | One Model to Rule them All: Towards Zero-Shot Learning for Databases | 2022 | CIDR |
| 5 | 4,726 | Learned Index Benefits: Machine Learning Based Index Performance Estimation | 2022 | VLDB |
| 6 | 5,484 | A Comparative Study and Component Analysis of Query Plan Representation Techniques in ML4DB Studies | 2024 | VLDB |
| 7 | 9,995 | Graph Transformers for Query Plan Representation: Potentials and Challenges | 2025 | VLDB |
| 8 | 6,402 | A Unified Transferable Model for ML-Enhanced DBMS | 2022 | CIDR |
| 9 | 5,211 | Database Workload Characterization with Query Plan Encoders | 2022 | VLDB |
| 10 | 2,169 | QueryFormer: A Tree Transformer Model for Query Plan Representation | 2022 | VLDB |