Graph Transformers for Query Plan Representation: Potentials and Challenges
Summary: Finds Graph Transformer Networks (GTNs) excel at query-plan representation (new taxonomy) but degrade with scarce training data. Proposes data augmentation and replacing LM-style components in GTNs, yielding SOTA on JOB/TPC-H/TPC-DS and TPC-DS→TPC-H transfer. (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. Chenghao Lyu (University of Massachusetts Amherst)
- 2. Guillaume Lachaud (Ecole Polytechnique)
- 3. Gabriel Lozano (Ecole Polytechnique)
- 4. Yanlei Diao (Ecole Polytechnique; University of Massachusetts Amherst)
BibTeX Citation
@article{lyu_vldb25,
title = {{Graph Transformers for Query Plan Representation: Potentials and Challenges}},
author = {Lyu, Chenghao and Lachaud, Guillaume and Lozano, Gabriel and Diao, Yanlei},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {13},
pages = {5716--5730},
doi = {10.14778/3773731.3773745},
url = {https://doi.org/10.14778/3773731.3773745},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 52 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,643 | PACE: Poisoning Attacks on Learned Cardinality Estimation | 2024 | SIGMOD | 5.3940849e-05 |
| 9,123 | BASE: Bridging the Gap between Cost and Latency for Query Optimization | 2023 | VLDB | 5.3193264e-05 |
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,836 | Transformers for Tabular Data Representation: A Tutorial on Models and Applications | 2022 | VLDB |
| 2 | 3,338 | Robust Query Driven Cardinality Estimation under Changing Workloads | 2023 | VLDB |
| 3 | 4,671 | PreQR: Pre-training Representation for SQL Understanding | 2022 | SIGMOD |
| 4 | 5,767 | A Comparative Study and Component Analysis of Query Plan Representation Techniques in ML4DB Studies | 2024 | VLDB |
| 5 | 10,830 | PlanRGCN: Predicting SPARQL Query Performance | 2025 | VLDB |
| 6 | 11,067 | Machine Learning for Graph Data Management and Query Processing | 2025 | VLDB |
| 7 | 2,812 | Query Performance Prediction for Concurrent Queries using Graph Embedding | 2020 | VLDB |
| 8 | 563 | Plan-Structured Deep Neural Network Models for Query Performance Prediction | 2019 | VLDB |
| 9 | 5,073 | Database Workload Characterization with Query Plan Encoders | 2022 | VLDB |
| 10 | 2,355 | QueryFormer: A Tree Transformer Model for Query Plan Representation | 2022 | VLDB |