Publikation
Opening The Black-Box: Explaining Learned Cost Models For Databases
Roman Heinrich; Oleksandr Havrylov; Manisha Luthra; Johannes Wehrstein; Carsten Binnig
In: Proceedings of the VLDB Endowment (PVLDB), Vol. 18, No. 12, Pages 5255-5258, arXiv, 2025.
Zusammenfassung
Learned Cost Models (LCMs) have shown superior results over tra-
ditional database cost models as they can significantly improve
the accuracy of cost predictions. However, LCMs still fail for some
query plans, as prediction errors can be large in the tail. Unfortu-
nately, recent LCMs are based on complex deep neural models, and
thus, there is no easy way to understand where this accuracy drop
is rooted, which critically prevents systematic troubleshooting. In
this demo paper, we present the very first approach for opening
the black box by bringing AI explainability approaches to LCM s.
As a core contribution, we developed new explanation techniques
that extend existing methods that are available for the general ex-
plainability of AI models and adapt them significantly to be usable
for LCMs. In our demo, we provide an interactive tool to showcase
how explainability for LCMs works. We believe this is a first step
for making LCMs debuggable and thus paving the road for new
approaches for systematically fixing problems in LCMs.