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
- 2. Guillaume Lachaud
- 3. Gabriel Lozano
- 4. Yanlei Diao
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 |
|---|---|---|---|---|
| 9,107 | BASE: Bridging the Gap between Cost and Latency for Query Optimization | 2023 | VLDB | 4.3907944e-05 |
| 9,215 | PACE: Poisoning Attacks on Learned Cardinality Estimation | 2024 | SIGMOD | 4.3679174e-05 |