PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning

While a number of knowledge graph representation learning (KGRL) methods have been proposed over the past decade, very few theoretical analyses have been conducted on them. In this paper, we present the first PAC-Bayesian generalization bounds for KGRL methods. To analyze a broad class of KGRL model...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Jaejun, Hwang, Minsung, Whang, Joyce Jiyoung
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Lee, Jaejun
Hwang, Minsung
Whang, Joyce Jiyoung
description While a number of knowledge graph representation learning (KGRL) methods have been proposed over the past decade, very few theoretical analyses have been conducted on them. In this paper, we present the first PAC-Bayesian generalization bounds for KGRL methods. To analyze a broad class of KGRL models, we propose a generic framework named ReED (Relation-aware Encoder-Decoder), which consists of a relation-aware message passing encoder and a triplet classification decoder. Our ReED framework can express at least 15 different existing KGRL models, including not only graph neural network-based models such as R-GCN and CompGCN but also shallow-architecture models such as RotatE and ANALOGY. Our generalization bounds for the ReED framework provide theoretical grounds for the commonly used tricks in KGRL, e.g., parameter-sharing and weight normalization schemes, and guide desirable design choices for practical KGRL methods. We empirically show that the critical factors in our generalization bounds can explain actual generalization errors on three real-world knowledge graphs.
doi_str_mv 10.48550/arxiv.2405.06418
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2405_06418</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2405_06418</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-b8fdbf22bbb0d0994f5d9eb06d343e15093c081f75a7f627031cab859b6033773</originalsourceid><addsrcrecordid>eNotz71OwzAUhmEvDKhwAUz1DSScxHbsjG0EAREBqrpHx_VxsRScyCk_5eoRLdO3vPqkh7GbAnJplIJbTN_hMy8lqBwqWZhL9vy6arI1HmkOGHlLkRIO4QcPYYx8PX5EN3M_Jv4Ux6-B3J54m3B64xuaEs0UD-eyI0wxxP0Vu_A4zHT9vwu2vb_bNg9Z99I-Nqsuw0qbzBrvrC9Lay04qGvplavJQuWEFFQoqMUOTOG1Qu2rUoModmiNqm0FQmgtFmx5vj2B-imFd0zH_g_Wn2DiF6E6SLQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning</title><source>arXiv.org</source><creator>Lee, Jaejun ; Hwang, Minsung ; Whang, Joyce Jiyoung</creator><creatorcontrib>Lee, Jaejun ; Hwang, Minsung ; Whang, Joyce Jiyoung</creatorcontrib><description>While a number of knowledge graph representation learning (KGRL) methods have been proposed over the past decade, very few theoretical analyses have been conducted on them. In this paper, we present the first PAC-Bayesian generalization bounds for KGRL methods. To analyze a broad class of KGRL models, we propose a generic framework named ReED (Relation-aware Encoder-Decoder), which consists of a relation-aware message passing encoder and a triplet classification decoder. Our ReED framework can express at least 15 different existing KGRL models, including not only graph neural network-based models such as R-GCN and CompGCN but also shallow-architecture models such as RotatE and ANALOGY. Our generalization bounds for the ReED framework provide theoretical grounds for the commonly used tricks in KGRL, e.g., parameter-sharing and weight normalization schemes, and guide desirable design choices for practical KGRL methods. We empirically show that the critical factors in our generalization bounds can explain actual generalization errors on three real-world knowledge graphs.</description><identifier>DOI: 10.48550/arxiv.2405.06418</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2024-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2405.06418$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2405.06418$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Lee, Jaejun</creatorcontrib><creatorcontrib>Hwang, Minsung</creatorcontrib><creatorcontrib>Whang, Joyce Jiyoung</creatorcontrib><title>PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning</title><description>While a number of knowledge graph representation learning (KGRL) methods have been proposed over the past decade, very few theoretical analyses have been conducted on them. In this paper, we present the first PAC-Bayesian generalization bounds for KGRL methods. To analyze a broad class of KGRL models, we propose a generic framework named ReED (Relation-aware Encoder-Decoder), which consists of a relation-aware message passing encoder and a triplet classification decoder. Our ReED framework can express at least 15 different existing KGRL models, including not only graph neural network-based models such as R-GCN and CompGCN but also shallow-architecture models such as RotatE and ANALOGY. Our generalization bounds for the ReED framework provide theoretical grounds for the commonly used tricks in KGRL, e.g., parameter-sharing and weight normalization schemes, and guide desirable design choices for practical KGRL methods. We empirically show that the critical factors in our generalization bounds can explain actual generalization errors on three real-world knowledge graphs.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz71OwzAUhmEvDKhwAUz1DSScxHbsjG0EAREBqrpHx_VxsRScyCk_5eoRLdO3vPqkh7GbAnJplIJbTN_hMy8lqBwqWZhL9vy6arI1HmkOGHlLkRIO4QcPYYx8PX5EN3M_Jv4Ux6-B3J54m3B64xuaEs0UD-eyI0wxxP0Vu_A4zHT9vwu2vb_bNg9Z99I-Nqsuw0qbzBrvrC9Lay04qGvplavJQuWEFFQoqMUOTOG1Qu2rUoModmiNqm0FQmgtFmx5vj2B-imFd0zH_g_Wn2DiF6E6SLQ</recordid><startdate>20240510</startdate><enddate>20240510</enddate><creator>Lee, Jaejun</creator><creator>Hwang, Minsung</creator><creator>Whang, Joyce Jiyoung</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20240510</creationdate><title>PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning</title><author>Lee, Jaejun ; Hwang, Minsung ; Whang, Joyce Jiyoung</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-b8fdbf22bbb0d0994f5d9eb06d343e15093c081f75a7f627031cab859b6033773</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Lee, Jaejun</creatorcontrib><creatorcontrib>Hwang, Minsung</creatorcontrib><creatorcontrib>Whang, Joyce Jiyoung</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lee, Jaejun</au><au>Hwang, Minsung</au><au>Whang, Joyce Jiyoung</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning</atitle><date>2024-05-10</date><risdate>2024</risdate><abstract>While a number of knowledge graph representation learning (KGRL) methods have been proposed over the past decade, very few theoretical analyses have been conducted on them. In this paper, we present the first PAC-Bayesian generalization bounds for KGRL methods. To analyze a broad class of KGRL models, we propose a generic framework named ReED (Relation-aware Encoder-Decoder), which consists of a relation-aware message passing encoder and a triplet classification decoder. Our ReED framework can express at least 15 different existing KGRL models, including not only graph neural network-based models such as R-GCN and CompGCN but also shallow-architecture models such as RotatE and ANALOGY. Our generalization bounds for the ReED framework provide theoretical grounds for the commonly used tricks in KGRL, e.g., parameter-sharing and weight normalization schemes, and guide desirable design choices for practical KGRL methods. We empirically show that the critical factors in our generalization bounds can explain actual generalization errors on three real-world knowledge graphs.</abstract><doi>10.48550/arxiv.2405.06418</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2405.06418
ispartof
issn
language eng
recordid cdi_arxiv_primary_2405_06418
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Learning
Statistics - Machine Learning
title PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T22%3A21%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=PAC-Bayesian%20Generalization%20Bounds%20for%20Knowledge%20Graph%20Representation%20Learning&rft.au=Lee,%20Jaejun&rft.date=2024-05-10&rft_id=info:doi/10.48550/arxiv.2405.06418&rft_dat=%3Carxiv_GOX%3E2405_06418%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true