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

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

Publikation: Beitrag in einer FachzeitschriftKonferenzartikelBegutachtung

Abstract

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.
Originalspracheenglisch
Seiten (von - bis)401-412
FachzeitschriftProceedings of Machine Learning Research
Jahrgang138
PublikationsstatusVeröffentlicht - 2020
Extern publiziertJa

Fingerprint

Untersuchen Sie die Forschungsthemen von „Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures.“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren