Inference with aggregation parfactors: Lifted elimination with first-order d-separation

Felipe Iwao Takiyama; Fabio Gagliardi Cozman

doi:10.1109/BRACIS.2014.75

Inference with aggregation parfactors: Lifted elimination with first-order d-separation

Felipe Iwao Takiyama, Fabio Gagliardi Cozman

Research output: Contribution to conference › Conference Paper

1 Scopus citations

Abstract

© 2014 IEEE. In this paper we focus on lifted inference for statistical relational models, that is, inference that avoids complete grounding, in models that combine logical and probabilistic assertions. We focus on relational Bayesian networks that can be represented through par factors and aggregation par factors. We present a new elimination rule for lifted variable elimination, and show how to use first-order d-separation to extend the reach of existing elimination rules.

Original language	American English
Pages	384-389
Number of pages	6
DOIs	https://doi.org/10.1109/BRACIS.2014.75
State	Published - 1 Jan 2014
Externally published	Yes
Event	Proceedings - 2014 Brazilian Conference on Intelligent Systems, BRACIS 2014 - Duration: 1 Jan 2014 → …

Conference

Conference	Proceedings - 2014 Brazilian Conference on Intelligent Systems, BRACIS 2014
Period	1/01/14 → …

Access to Document

10.1109/BRACIS.2014.75

Cite this

@conference{941dbe38249d490482494d6b2c90eeea,

title = "Inference with aggregation parfactors: Lifted elimination with first-order d-separation",

abstract = "{\textcopyright} 2014 IEEE. In this paper we focus on lifted inference for statistical relational models, that is, inference that avoids complete grounding, in models that combine logical and probabilistic assertions. We focus on relational Bayesian networks that can be represented through par factors and aggregation par factors. We present a new elimination rule for lifted variable elimination, and show how to use first-order d-separation to extend the reach of existing elimination rules.",

author = "Takiyama, {Felipe Iwao} and Cozman, {Fabio Gagliardi}",

year = "2014",

month = jan,

day = "1",

doi = "10.1109/BRACIS.2014.75",

language = "American English",

pages = "384--389",

note = "Proceedings - 2014 Brazilian Conference on Intelligent Systems, BRACIS 2014 ; Conference date: 01-01-2014",

}

TY - CONF

T1 - Inference with aggregation parfactors: Lifted elimination with first-order d-separation

AU - Takiyama, Felipe Iwao

AU - Cozman, Fabio Gagliardi

PY - 2014/1/1

Y1 - 2014/1/1

N2 - © 2014 IEEE. In this paper we focus on lifted inference for statistical relational models, that is, inference that avoids complete grounding, in models that combine logical and probabilistic assertions. We focus on relational Bayesian networks that can be represented through par factors and aggregation par factors. We present a new elimination rule for lifted variable elimination, and show how to use first-order d-separation to extend the reach of existing elimination rules.

AB - © 2014 IEEE. In this paper we focus on lifted inference for statistical relational models, that is, inference that avoids complete grounding, in models that combine logical and probabilistic assertions. We focus on relational Bayesian networks that can be represented through par factors and aggregation par factors. We present a new elimination rule for lifted variable elimination, and show how to use first-order d-separation to extend the reach of existing elimination rules.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84922546758&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84922546758&origin=inward

U2 - 10.1109/BRACIS.2014.75

DO - 10.1109/BRACIS.2014.75

M3 - Conference Paper

SP - 384

EP - 389

T2 - Proceedings - 2014 Brazilian Conference on Intelligent Systems, BRACIS 2014

Y2 - 1 January 2014

ER -

Inference with aggregation parfactors: Lifted elimination with first-order d-separation

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this