文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > IT/计算机 > Probabilistic Graphical Models for Relational Data
侵权投诉

Probabilistic Graphical Models for Relational Data

An Introduction to Probabilistic Graphical Models for Relational Data 概率图模型

AnIntroductionto

ProbabilisticGraphicalModelsforRelationalData

LiseGetoor

ComputerScienceDepartment/UMIACS

UniversityofMaryland

CollegePark,MD20740

getoor@cs.umd.edu

Abstract

Wesurveysomeoftherecentworkonprobabilisticgraphicalmodelsforrelationaldata.Themodelsthatwedescribeareallbasedupon’graphicalmodels’[12].Themodelscancapturestatisticalcorrelationsamongattributeswithinasinglerelationaltable,betweenattributesindifferenttables,andcancapturecertainstructuralproperties,suchastheexpectedsizeofajoinbetweentables.Thesemodelscanthenbeusedforavarietyoftasksincluding llinginmissingvalues,datasummarizationandanomalydetection.Herewedescribetwocomplementarysemanticsforthemodels:oneapproachsuitedtomakingprobabilisticstatementsaboutindividualsandthesecondapproachsuitedtomakingstatementsaboutfrequenciesinrelationaldata.Afterdescribingthesemantics,webrie ydescribealgorithmsforautomaticallyconstructingthemodelsfromanexisting(non-probabilistic)database.

1Introduction

Therehasbeenagrowinginterestinprobabilisticdatabases.Thisgrowinginterestislargelyduetoexpandingdatacollectionopportunitiesandcapabilities.Inaddition,recentadvancesinprobabilisticmodeling,bothintermsofef cientlearningandestimationalgorithmsandpracticalinferencealgorithmshavemadetheuseofthesemodelsforlarge-scaledomainspractical.Inthissurveypaper,wereviewsomeoftheworkdevelopedintheprobabilisticreasoningandmachinelearningcommunitiescommonlyreferedtoasprobabilisticrelationalmodels(PRMs)[11].PRMsarebasedonexistingprobabilisticmodels(typicallyBayesiannetworks)andextendthemtorelationaland rst-orderdomains.

Halpern[9]identi edtwodistinctsemanticsfor rst-orderlogicsofprobability,referedtoasthepossible-worldsapproachandthedomain-frequencyapproach.Inthepossible-worldsapproach,weputadistributionoverpossibleworlds.Thedistributioncanbeusedtoanswerdegreeofbeliefquestionssuchas‘Whatistheprobabilitythataparticularperson,JoeSmith,haspurchasedaparticulartractorpart,WidgetSupreme?’.Inthiscase,thesemanticsoftheformulaisde nedbysumminguptheprobabilityoverallofthepossibleworldsinwhichJoeSmithhasboughtWidgetSupremes.However,asmanyhavenoted[2,1],therearedif cultieswithmakingstatisticalassertions,suchas‘75%ofthepurchaseswereforwidgets’.Thesecondapproach,referedto

1

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email