MoEPlan: A Lazy Learned Query-Selection Optimizer via Mixture of Optimizer Experts
ACM Transactions on Knowledge Discovery from Data · 31.05.2026 · 20 (4) · 1-26
DOI: 10.1145/3800575 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 10.04.2026. Verfasst von Suchen Liu und 3 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, ZTE-PKU joint program.
Abstract (Originalsprache)
Learned plan-selection optimizers combine the conventional and learned approaches by generating diverse candidate plans through multiple optimizers and selecting the best via value models. However, these eagerly-generated plans incur high optimization overhead, as they require multiple invocations of the native optimizer. In this article, we propose MoEPlan, which learns a routing policy to select top- \( k \) experts (different optimizers) via query embedding and learnable parameters, avoiding pre-generation of candidate plans. Our approach integrates two optimization strategies: (1) a virtual ideal expert to guide the best plan selection through learned plan similarities, and (2) a query-irrelevant expert sampling strategy to balance the training cost and effectiveness of selected plans in the first round of expert selection. Furthermore, we design a two-phase training process: the first phase pre-trains the model with complete expert feedback, while the second phase filters the full expert pool to yield a promising subset and refines the selection to pinpoint the optimal expert. Experimental studies show that MoEPlan, with only two plans generated, takes less inference time, while still producing more efficient plans than other learned plan-selection optimizers.
Förderung
- National Natural Science Foundation of China
- ZTE-PKU joint program
Zitieren
APA
Liu, S., Gao, J., Han, Y., & Lin, Y. (2026). MoEPlan: A Lazy Learned Query-Selection Optimizer via Mixture of Optimizer Experts. ACM Transactions on Knowledge Discovery from Data, 20(4), 1-26. https://doi.org/10.1145/3800575
Vancouver
Liu S, Gao J, Han Y, Lin Y. MoEPlan: A Lazy Learned Query-Selection Optimizer via Mixture of Optimizer Experts. ACM Transactions on Knowledge Discovery from Data. 2026;20(4):1-26. doi:10.1145/3800575
BibTeX
@article{Liu2026,
author = {Liu, Suchen and Gao, Jun and Han, Yinjun and Lin, Yang},
title = {MoEPlan: A Lazy Learned Query-Selection Optimizer via Mixture of Optimizer Experts},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2026},
volume = {20},
number = {4},
pages = {1--26},
doi = {10.1145/3800575}
}
EUVIMED