Inference in Probabilistic Graphical Models by Graph Neural Networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yoon, Ki jung | - |
dc.contributor.author | Liao, Renjie | - |
dc.contributor.author | Xiong, Yuwen | - |
dc.contributor.author | Zhang, Lisa | - |
dc.contributor.author | Fetaya, Ethan | - |
dc.contributor.author | Urtasun, Raquel | - |
dc.contributor.author | Zemel, Richard | - |
dc.contributor.author | Pitkow, Xaq | - |
dc.date.accessioned | 2021-07-30T05:24:21Z | - |
dc.date.available | 2021-07-30T05:24:21Z | - |
dc.date.created | 2021-05-13 | - |
dc.date.issued | 2019-03 | - |
dc.identifier.issn | 1058-6393 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/4605 | - |
dc.description.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. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Inference in Probabilistic Graphical Models by Graph Neural Networks | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Yoon, Ki jung | - |
dc.identifier.doi | 10.1109/IEEECONF44664.2019.9048920 | - |
dc.identifier.scopusid | 2-s2.0-85083329103 | - |
dc.identifier.wosid | 000544249200168 | - |
dc.identifier.bibliographicCitation | Conference Record - Asilomar Conference on Signals, Systems and Computers, v.2019-November, pp.868 - 875 | - |
dc.relation.isPartOf | Conference Record - Asilomar Conference on Signals, Systems and Computers | - |
dc.citation.title | Conference Record - Asilomar Conference on Signals, Systems and Computers | - |
dc.citation.volume | 2019-November | - |
dc.citation.startPage | 868 | - |
dc.citation.endPage | 875 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordPlus | BELIEF PROPAGATION | - |
dc.subject.keywordPlus | PRODUCT | - |
dc.subject.keywordPlus | Backpropagation | - |
dc.subject.keywordPlus | Binary codes | - |
dc.subject.keywordPlus | Computer circuits | - |
dc.subject.keywordPlus | Decision making | - |
dc.subject.keywordPlus | Graph structures | - |
dc.subject.keywordPlus | Graphic methods | - |
dc.subject.keywordPlus | Inference engines | - |
dc.subject.keywordPlus | Message passing | - |
dc.subject.keywordPlus | Belief propagation | - |
dc.subject.keywordPlus | Correlated variables | - |
dc.subject.keywordPlus | Different structure | - |
dc.subject.keywordPlus | Graph neural networks | - |
dc.subject.keywordPlus | Marginal probability | - |
dc.subject.keywordPlus | Message passing algorithm | - |
dc.subject.keywordPlus | Probabilistic graphical models | - |
dc.subject.keywordPlus | Statistical inference | - |
dc.subject.keywordPlus | Graph algorithms | - |
dc.subject.keywordAuthor | graph neural networks | - |
dc.subject.keywordAuthor | inference | - |
dc.subject.keywordAuthor | message-passing | - |
dc.subject.keywordAuthor | probabilistic graphical models | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9048920 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.