Transparency in Sum-Product Network Decompilation

Giannis Papantonis, Vaishak Belle

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Sum-product networks guarantee that conditionals and marginals can be computed efficiently, for a wide range of models, bypassing the hardness of inference. However, this advantage comes at the expense of transparency, since it is unclear how variables inter act in sum-product networks. Due to this, a series of decompilation algorithms transform sum-product networks back to Bayesian networks. In this work, we first study the transparency and causal utility of the resulting Bayesian networks. We then propose a novel decompilation algorithm to address the identified limitations.
Original languageEnglish
Title of host publicationProceedings of the 26th European Conference on Artificial Intelligence
PublisherIOS Press
Number of pages8
ISBN (Electronic)9781643684376
ISBN (Print)9781643684369
Publication statusPublished - 1 Oct 2023
Event26th European Conference on Artificial Intelligence - ICE Kraków Congress Centre, Kraków, Poland
Duration: 30 Sept 20235 Oct 2023

Publication series

NameFrontiers in Artificial Intelligence and Applications
PublisherIOS Press
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314


Conference26th European Conference on Artificial Intelligence
Abbreviated titleECAI 2023
Internet address


Dive into the research topics of 'Transparency in Sum-Product Network Decompilation'. Together they form a unique fingerprint.

Cite this