Saved in:
Bibliographic Details
Main Authors: Papež, Milan, Rektoris, Martin, Pevný, Tomáš, Šmídl, Václav
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.07394
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913470797053952
author Papež, Milan
Rektoris, Martin
Pevný, Tomáš
Šmídl, Václav
author_facet Papež, Milan
Rektoris, Martin
Pevný, Tomáš
Šmídl, Václav
contents Daily internet communication relies heavily on tree-structured graphs, embodied by popular data formats such as XML and JSON. However, many recent generative (probabilistic) models utilize neural networks to learn a probability distribution over undirected cyclic graphs. This assumption of a generic graph structure brings various computational challenges, and, more importantly, the presence of non-linearities in neural networks does not permit tractable probabilistic inference. We address these problems by proposing sum-product-set networks, an extension of probabilistic circuits from unstructured tensor data to tree-structured graph data. To this end, we use random finite sets to reflect a variable number of nodes and edges in the graph and to allow for exact and efficient inference. We demonstrate that our tractable model performs comparably to various intractable models based on neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2408_07394
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs
Papež, Milan
Rektoris, Martin
Pevný, Tomáš
Šmídl, Václav
Machine Learning
Artificial Intelligence
Daily internet communication relies heavily on tree-structured graphs, embodied by popular data formats such as XML and JSON. However, many recent generative (probabilistic) models utilize neural networks to learn a probability distribution over undirected cyclic graphs. This assumption of a generic graph structure brings various computational challenges, and, more importantly, the presence of non-linearities in neural networks does not permit tractable probabilistic inference. We address these problems by proposing sum-product-set networks, an extension of probabilistic circuits from unstructured tensor data to tree-structured graph data. To this end, we use random finite sets to reflect a variable number of nodes and edges in the graph and to allow for exact and efficient inference. We demonstrate that our tractable model performs comparably to various intractable models based on neural networks.
title Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.07394