Publikation
How Good are Learned Cost Models, Really? Insights from Query Optimization Tasks
Roman Heinrich; Manisha Luthra; Johannes Wehrstein; Harald Kornmayer; Carsten Binnig
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2502.01229, Pages 1-27, arXiv, 2025.
Zusammenfassung
Traditionally, query optimizers rely on cost models to choose the best execution plan from several candidates,
making precise cost estimates critical for efficient query execution. In recent years, cost models based on
machine learning have been proposed to overcome the weaknesses of traditional cost models. While these
models have been shown to provide better prediction accuracy, only limited efforts have been made to
investigate how well Learned Cost Models (LCMs) actually perform in query optimization and how they affect
overall query performance. In this paper, we address this by a systematic study evaluating LCM s on three of
the core query optimization tasks: join ordering, access path selection, and physical operator selection. In our
study, we compare seven state-of-the-art LCM s to a traditional cost model and, surprisingly, find that the
traditional model often still outperforms LCMs in these tasks. We conclude by highlighting major takeaways
and recommendations to guide future research toward making LCMs more effective for query optimization.