LengthPath: The Length Reward of Knowledge Graph Reasoning Based on Deep Reinforcement Learning
Knowledge Graph (KG) always suffers from incompleteness. Knowledge Graph Reasoning (KGR) aims to predict the unknown entity or find reasoning paths for relations over incomplete KG. However, multi-hop reasoning still facing challenges, because the process of reasoning usually experiences the neighbo...
Saved in:
Published in | 2024 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 8 |
---|---|
Main Authors | , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
30.06.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Knowledge Graph (KG) always suffers from incompleteness. Knowledge Graph Reasoning (KGR) aims to predict the unknown entity or find reasoning paths for relations over incomplete KG. However, multi-hop reasoning still facing challenges, because the process of reasoning usually experiences the neighbor information issue. Prior works just use path efficiency as a part of reward function and do not utilize the neighbor information effectively. In order to deal with the situation, we propose the length reward in the Reinforcement Learning (RL) framework to represent the length of reasoning paths and use the neighbor information effectively. Our model utilizes the position information to design reward function. To solve this problem of save the semantic information of entity neighbors and historical trajectory information, we propose a new GRU-GAT framework to capture neighbor feature of the current entity and the target entity. Experimental results on NELL-995 and FB15K237 demonstrate the effectiveness of our model and our model can identify a more balanced route for every relation. |
---|---|
AbstractList | Knowledge Graph (KG) always suffers from incompleteness. Knowledge Graph Reasoning (KGR) aims to predict the unknown entity or find reasoning paths for relations over incomplete KG. However, multi-hop reasoning still facing challenges, because the process of reasoning usually experiences the neighbor information issue. Prior works just use path efficiency as a part of reward function and do not utilize the neighbor information effectively. In order to deal with the situation, we propose the length reward in the Reinforcement Learning (RL) framework to represent the length of reasoning paths and use the neighbor information effectively. Our model utilizes the position information to design reward function. To solve this problem of save the semantic information of entity neighbors and historical trajectory information, we propose a new GRU-GAT framework to capture neighbor feature of the current entity and the target entity. Experimental results on NELL-995 and FB15K237 demonstrate the effectiveness of our model and our model can identify a more balanced route for every relation. |
Author | Zi-Hao, Li Jie-Wei, Li Ling, Yue Qiu-Ping, Shuai Lin, Feng Ling-Xiao, Xu |
Author_xml | – sequence: 1 givenname: Xu surname: Ling-Xiao fullname: Ling-Xiao, Xu email: jayxlx@stu.sicnu.edu.cn organization: SiChuan Normal University,School of Computer Science,ChengDu,China – sequence: 2 givenname: Feng surname: Lin fullname: Lin, Feng email: fenglin@stu.sicnu.edu.cn organization: SiChuan Normal University,School of Computer Science,ChengDu,China – sequence: 3 givenname: Li surname: Zi-Hao fullname: Zi-Hao, Li email: li_zihao@stu.sicnu.edu.cn organization: SiChuan Normal University,School of Computer Science,ChengDu,China – sequence: 4 givenname: Yue surname: Ling fullname: Ling, Yue email: 20221302005@stu.sicnu.edu.cn organization: SiChuan Normal University,School of Computer Science,ChengDu,China – sequence: 5 givenname: Shuai surname: Qiu-Ping fullname: Qiu-Ping, Shuai email: qiuping@stu.sicnu.edu.cn organization: SiChuan Normal University,School of Computer Science,ChengDu,China – sequence: 6 givenname: Li surname: Jie-Wei fullname: Jie-Wei, Li email: lijiewei@stu.sicnu.edu.cn organization: SiChuan Normal University,School of Computer Science,ChengDu,China |
BookMark | eNqFjs1OAkEQhBujiaC8AYd-AZaemd2F8Sj-giHGcN9MpPfHQM9mZhPi27tEPXOqVH2VSo3gUrwwACpKlCI7e10tN5ucFtYmmnSaKMozyigdwNjO7cJkZDJrlL6AoVa5mqYpza9hFOMXkTbWmiEUbyxVV7-7rr7Dbc346_GDjy7s0Je4Fn_c865ifA6uPREXvTRS4b2L3FcEH5jbPm-k9OGTDyxdP-PCqXQLV6XbRx7_6Q1Mnh63y5dpw8xFG5qDC9_F_3FzBv8ADWRIuA |
ContentType | Conference Proceeding |
DBID | 6IE 6IH CBEJK RIE RIO |
DOI | 10.1109/IJCNN60899.2024.10650504 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library IEEE Proceedings Order Plans (POP) 1998-present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Xplore url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISBN | 9798350359312 |
EISSN | 2161-4407 |
EndPage | 8 |
ExternalDocumentID | 10650504 |
Genre | orig-research |
GroupedDBID | 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI OCL RIE RIL RIO RNS |
ID | FETCH-ieee_primary_106505043 |
IEDL.DBID | RIE |
IngestDate | Wed Sep 18 05:50:08 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-ieee_primary_106505043 |
ParticipantIDs | ieee_primary_10650504 |
PublicationCentury | 2000 |
PublicationDate | 2024-June-30 |
PublicationDateYYYYMMDD | 2024-06-30 |
PublicationDate_xml | – month: 06 year: 2024 text: 2024-June-30 day: 30 |
PublicationDecade | 2020 |
PublicationTitle | 2024 International Joint Conference on Neural Networks (IJCNN) |
PublicationTitleAbbrev | IJCNN |
PublicationYear | 2024 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
SSID | ssj0023993 |
Score | 3.8609633 |
Snippet | Knowledge Graph (KG) always suffers from incompleteness. Knowledge Graph Reasoning (KGR) aims to predict the unknown entity or find reasoning paths for... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 1 |
SubjectTerms | Cognition Deep reinforcement learning Knowledge Graph Reasoning Knowledge graphs length reward Neural networks Reinforcement Learning Semantics Statistical analysis Trajectory |
Title | LengthPath: The Length Reward of Knowledge Graph Reasoning Based on Deep Reinforcement Learning |
URI | https://ieeexplore.ieee.org/document/10650504 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT4NAEJ5oT57qA-Ojmjl4BRGW0nq0WmtV0hhNeiOwO9TEBJoKF3-9swvUaDTxBstrssvk25n95luAM8aITClP2YEMpS0kB6yJlwlbummQytAnoXSh8GPUn7yI6TyYN8XqphaGiAz5jBx9aNbyVSErnSpjD-f5RKDVPzcHrlcXa62jK420LVXHHZ7fTUdR1NeLWhwEesJpn_22i4oBkXEXovbzNXfkzanK1JEfP5QZ_23fNlhf9Xo4WyPRDmxQvgvddsMGbPx3D-IHyhfl64xnfZfIPwjW5_hEmjuLRYb3bYoNb7WSNV9J3k3CFq8Y7viWHK-JltxuFFelSS5iI9K6sKA3vnkeTWxtdLyshSzi1l5_Hzp5kdMBoJtKjriSzPdCJRJBQ_bogQwvyNcaj4oOwfr1FUd_tB_Dlu7-mmHXg065quiEYbxMT83wfQJ6rKEI |
link.rule.ids | 310,311,786,790,795,796,802,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1NT4NAEJ2YetBT_cD4UXUPXkGEpViPVittKWlMTXojsDu0iQk0Si_-emcXqNFo4g12FzLJ7uTtzM57C3BFGJFJ6UjTE74wuaCANXEybgo79VLhu8ilIgpPom7wwkdzb16T1TUXBhF18Rla6lGf5ctCrFWqjDyc9hOeUv_cJqC3_YqutYmvFNY2xTp273o46kdRVx1rURjocKv5-ts9KhpGBm2IGgOq6pFXa12mlvj4oc34bwv3wPhi7LHpBov2YQvzA2g3Vzaw2oMPIQ4xX5TLKe377hgtEVa9s2dU1bOsyNi4SbKxJ6VlTT3Ju07ZsnsCPBqSswfEFbVrzVWh04uslmldGNAZPM76gamMjleVlEXc2OseQSsvcjwGZqeCYq4kcx1f8oRjj3z6Vvg36CqVR4knYPz6i9M_2i9hJ5hNwjgcRuMz2FVTUdXbdaBVvq3xnEC9TC_0VH4CJFakXA |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2024+International+Joint+Conference+on+Neural+Networks+%28IJCNN%29&rft.atitle=LengthPath%3A+The+Length+Reward+of+Knowledge+Graph+Reasoning+Based+on+Deep+Reinforcement+Learning&rft.au=Ling-Xiao%2C+Xu&rft.au=Lin%2C+Feng&rft.au=Zi-Hao%2C+Li&rft.au=Ling%2C+Yue&rft.date=2024-06-30&rft.pub=IEEE&rft.eissn=2161-4407&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FIJCNN60899.2024.10650504&rft.externalDocID=10650504 |