Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00374040" target="_blank" >RIV/68407700:21230/24:00374040 - isvavai.cz</a>

Result on the web

<a href="https://openreview.net/forum?id=mF3cTns4pe" target="_blank" >https://openreview.net/forum?id=mF3cTns4pe</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA22-32620S" target="_blank" >GA22-32620S: Unsupervised learning from heterogenous structured data</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceeding The Twelfth International Conference on Learning Representations (ICLR 2024)

ISBN

9781713898658

ISSN

—

e-ISSN

—

Number of pages

30

Pages from-to

—

Publisher name

International Conference on Learning Representations

Place of publication

—

Event location

Vídeň

Event date

May 7, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—