How to Turn Your Knowledge Graph Embeddings into Generative Models

Some of the most successful knowledge graph embedding (KGE) models for link prediction -- CP, RESCAL, TuckER, ComplEx -- can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2023-10
Hauptverfasser: Loconte, Lorenzo, Nicola Di Mauro, Peharz, Robert, Vergari, Antonio
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Loconte, Lorenzo
Nicola Di Mauro
Peharz, Robert
Vergari, Antonio
description Some of the most successful knowledge graph embedding (KGE) models for link prediction -- CP, RESCAL, TuckER, ComplEx -- can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical constraints. This work re-interprets the score functions of these KGEs as circuits -- constrained computational graphs allowing efficient marginalisation. Then, we design two recipes to obtain efficient generative circuit models by either restricting their activations to be non-negative or squaring their outputs. Our interpretation comes with little or no loss of performance for link prediction, while the circuits framework unlocks exact learning by MLE, efficient sampling of new triples, and guarantee that logical constraints are satisfied by design. Furthermore, our models scale more gracefully than the original KGEs on graphs with millions of entities.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2819553293</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2819553293</sourcerecordid><originalsourceid>FETCH-proquest_journals_28195532933</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRw8sgvVyjJVwgpLcpTiMwvLVLwzssvz0lNSU9VcC9KLMhQcM1NSk1JycxLL1bIzAOqdE_NSy1KLMksS1XwzU9JzSnmYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8VlAc_OAUvFGFoaWQGuNLI2NiVMFAHIAOVo</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2819553293</pqid></control><display><type>article</type><title>How to Turn Your Knowledge Graph Embeddings into Generative Models</title><source>Free E- Journals</source><creator>Loconte, Lorenzo ; Nicola Di Mauro ; Peharz, Robert ; Vergari, Antonio</creator><creatorcontrib>Loconte, Lorenzo ; Nicola Di Mauro ; Peharz, Robert ; Vergari, Antonio</creatorcontrib><description>Some of the most successful knowledge graph embedding (KGE) models for link prediction -- CP, RESCAL, TuckER, ComplEx -- can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical constraints. This work re-interprets the score functions of these KGEs as circuits -- constrained computational graphs allowing efficient marginalisation. Then, we design two recipes to obtain efficient generative circuit models by either restricting their activations to be non-negative or squaring their outputs. Our interpretation comes with little or no loss of performance for link prediction, while the circuits framework unlocks exact learning by MLE, efficient sampling of new triples, and guarantee that logical constraints are satisfied by design. Furthermore, our models scale more gracefully than the original KGEs on graphs with millions of entities.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Circuit design ; Constraints ; Graphs ; Knowledge representation ; Maximum likelihood estimation ; Sampling</subject><ispartof>arXiv.org, 2023-10</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Loconte, Lorenzo</creatorcontrib><creatorcontrib>Nicola Di Mauro</creatorcontrib><creatorcontrib>Peharz, Robert</creatorcontrib><creatorcontrib>Vergari, Antonio</creatorcontrib><title>How to Turn Your Knowledge Graph Embeddings into Generative Models</title><title>arXiv.org</title><description>Some of the most successful knowledge graph embedding (KGE) models for link prediction -- CP, RESCAL, TuckER, ComplEx -- can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical constraints. This work re-interprets the score functions of these KGEs as circuits -- constrained computational graphs allowing efficient marginalisation. Then, we design two recipes to obtain efficient generative circuit models by either restricting their activations to be non-negative or squaring their outputs. Our interpretation comes with little or no loss of performance for link prediction, while the circuits framework unlocks exact learning by MLE, efficient sampling of new triples, and guarantee that logical constraints are satisfied by design. Furthermore, our models scale more gracefully than the original KGEs on graphs with millions of entities.</description><subject>Circuit design</subject><subject>Constraints</subject><subject>Graphs</subject><subject>Knowledge representation</subject><subject>Maximum likelihood estimation</subject><subject>Sampling</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRw8sgvVyjJVwgpLcpTiMwvLVLwzssvz0lNSU9VcC9KLMhQcM1NSk1JycxLL1bIzAOqdE_NSy1KLMksS1XwzU9JzSnmYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8VlAc_OAUvFGFoaWQGuNLI2NiVMFAHIAOVo</recordid><startdate>20231029</startdate><enddate>20231029</enddate><creator>Loconte, Lorenzo</creator><creator>Nicola Di Mauro</creator><creator>Peharz, Robert</creator><creator>Vergari, Antonio</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231029</creationdate><title>How to Turn Your Knowledge Graph Embeddings into Generative Models</title><author>Loconte, Lorenzo ; Nicola Di Mauro ; Peharz, Robert ; Vergari, Antonio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28195532933</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Circuit design</topic><topic>Constraints</topic><topic>Graphs</topic><topic>Knowledge representation</topic><topic>Maximum likelihood estimation</topic><topic>Sampling</topic><toplevel>online_resources</toplevel><creatorcontrib>Loconte, Lorenzo</creatorcontrib><creatorcontrib>Nicola Di Mauro</creatorcontrib><creatorcontrib>Peharz, Robert</creatorcontrib><creatorcontrib>Vergari, Antonio</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Loconte, Lorenzo</au><au>Nicola Di Mauro</au><au>Peharz, Robert</au><au>Vergari, Antonio</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>How to Turn Your Knowledge Graph Embeddings into Generative Models</atitle><jtitle>arXiv.org</jtitle><date>2023-10-29</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Some of the most successful knowledge graph embedding (KGE) models for link prediction -- CP, RESCAL, TuckER, ComplEx -- can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical constraints. This work re-interprets the score functions of these KGEs as circuits -- constrained computational graphs allowing efficient marginalisation. Then, we design two recipes to obtain efficient generative circuit models by either restricting their activations to be non-negative or squaring their outputs. Our interpretation comes with little or no loss of performance for link prediction, while the circuits framework unlocks exact learning by MLE, efficient sampling of new triples, and guarantee that logical constraints are satisfied by design. Furthermore, our models scale more gracefully than the original KGEs on graphs with millions of entities.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2819553293
source Free E- Journals
subjects Circuit design
Constraints
Graphs
Knowledge representation
Maximum likelihood estimation
Sampling
title How to Turn Your Knowledge Graph Embeddings into Generative Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T13%3A27%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=How%20to%20Turn%20Your%20Knowledge%20Graph%20Embeddings%20into%20Generative%20Models&rft.jtitle=arXiv.org&rft.au=Loconte,%20Lorenzo&rft.date=2023-10-29&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2819553293%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2819553293&rft_id=info:pmid/&rfr_iscdi=true