Inference in Probabilistic Graphical Models by Graph Neural Networks

Kijung Yoon, Renjie Liao, Yuwen Xiong, Lisa Zhang, Ethan Fetaya, Raquel Urtasun, Richard Zemel, Xaq Pitkow

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

27 Scopus citations

Abstract

A fundamental computation for statistical inference and accurate decision-making is to estimate the marginal probabilities or most probable states of task-relevant variables. Probabilistic graphical models can efficiently represent the structure of such complex data, but performing these inferences is generally difficult. Message-passing algorithms, such as belief propagation, are a natural way to disseminate evidence amongst correlated variables while exploiting the graph structure, but these algorithms can struggle when the conditional dependency graphs contain loops. Here we use Graph Neural Networks (GNNs) to learn a message-passing algorithm that solves these inference tasks. We first show that the architecture of GNNs is well-matched to inference tasks. We then demonstrate the efficacy of this inference approach by training GNNs on a collection of graphical models and showing that they substantially outperform belief propagation on loopy graphs. Our message-passing algorithms generalize out of the training set to larger graphs and graphs with different structure.

Original languageEnglish
Title of host publicationConference Record - 53rd Asilomar Conference on Circuits, Systems and Computers, ACSSC 2019
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages868-875
Number of pages8
ISBN (Electronic)9781728143002
DOIs
StatePublished - Nov 2019
Externally publishedYes
Event53rd Asilomar Conference on Circuits, Systems and Computers, ACSSC 2019 - Pacific Grove, United States
Duration: 3 Nov 20196 Nov 2019

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2019-November
ISSN (Print)1058-6393

Conference

Conference53rd Asilomar Conference on Circuits, Systems and Computers, ACSSC 2019
Country/TerritoryUnited States
CityPacific Grove
Period3/11/196/11/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

  • graph neural networks
  • inference
  • message-passing
  • probabilistic graphical models

Fingerprint

Dive into the research topics of 'Inference in Probabilistic Graphical Models by Graph Neural Networks'. Together they form a unique fingerprint.

Cite this