Athena: An Effective Learning-based Framework for Query Optimizer Performance Improvement
Summary: Athena is a learning-based framework that enhances query optimizer performance by expanding plan exploration and improving learning from executions. It features an order-centric plan explorer, a Tree-Mamba plan comparator, and a time-weighted loss, is implemented on PostgreSQL, and yields multi-benchmark speedups over vanilla PostgreSQL and Lero; open-sourced and portable. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Runzhong Li (Hong Kong Polytechnic University; Southern University of Science and Technology)
- 2. Qilong Li (Southern University of Science and Technology)
- 3. Haotian Liu (Southern University of Science and Technology)
- 4. Rui Mao (Shenzhen University)
- 5. Qing Li (Hong Kong Polytechnic University)
- 6. Bo Tang (Southern University of Science and Technology)
BibTeX Citation
@inproceedings{li_sigmod25,
title = {{Athena: An Effective Learning-based Framework for Query Optimizer Performance Improvement}},
author = {Li, Runzhong and Li, Qilong and Liu, Haotian and Mao, Rui and Li, Qing and Tang, Bo},
series = {{SIGMOD} '25},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3725395},
url = {https://dl.acm.org/doi/10.1145/3725395},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,515 | Sample-based Distinct Cardinality Estimation for Multiple Attributes in Multi-Dataset Queries | 2026 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 40 of 40 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 | 4,470 | Kepler: Robust Learning for Faster Parametric Query Optimization | 2023 | SIGMOD |
| 2 | 10,508 | Practical Parameterized Query Optimization via Efficient Plan Reuse and List-wise Ranking | 2026 | SIGMOD |
| 3 | 9,428 | LIMAO: A Framework for Lifelong Modular Learned Query Optimization | 2025 | VLDB |
| 4 | 2,762 | Cost-based or Learning-based? A Hybrid Query Optimizer for Query Plan Selection | 2022 | VLDB |
| 5 | 4,929 | AutoSteer: Learned Query Optimization for Any SQL Database | 2023 | VLDB |
| 6 | 154 | Neo: A Learned Query Optimizer | 2019 | VLDB |
| 7 | 11,103 | RankPQO: Learning-to-Rank for Parametric Query Optimization | 2025 | VLDB |
| 8 | 2,420 | Lero: A Learning-to-Rank Query Optimizer | 2023 | VLDB |
| 9 | 6,271 | Is Your Learned Query Optimizer Behaving As You Expect? A Machine Learning Perspective | 2024 | VLDB |
| 10 | 11,548 | DeepO: A Learned Query Optimizer | 2022 | SIGMOD |