Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures

Xiaoting Shao, Alejandro Molina, Antonio Vergari, Karl Stelzner, Robert Peharz, Thomas Liebig, Kristian Kersting

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


Probabilistic graphical models are a central tool in AI, however, they are generally not as expressive as deep neural models, and inference is notoriously hard and slow. In contrast, deep probabilistic models such as sum-product networks (SPNs) capture joint distributions in a tractable fashion, but still lack the expressive power of intractable models based on deep neural networks. Therefore, we introduce conditional SPNs (CSPNs), conditional density estimators for multivariate and potentially hybrid domains that allow harnessing the expressive power of neural networks while still maintaining tractability guarantees. One way to implement CSPNs is to use an existing SPN structure and condition its parameters on the input, e.g., via a deep neural network. Our experimental evidence demonstrates that CSPNs are competitive with other probabilistic models and yield superior performance on multilabel image classification compared to mean field and mixture density networks. Furthermore, they can successfully be employed as building blocks for structured probabilistic models, such as autoregressive image models.
Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Probabilistic Graphical Models
EditorsManfred Jaeger, Thomas Dyhre Nielsen
Number of pages12
Publication statusPublished - 23 Sep 2020
EventTenth International Conference on Probabilistic Graphical Models -
Duration: 23 Sep 202025 Sep 2020
Conference number: 10

Publication series

NameProceedings of Machine Learning Research
ISSN (Electronic)2640-3498


ConferenceTenth International Conference on Probabilistic Graphical Models
Abbreviated titlePGM 2020
Internet address


Dive into the research topics of 'Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures'. Together they form a unique fingerprint.

Cite this