Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective
Benefiting from the injection of human prior knowledge, graphs, as derived discrete data, are semantically dense so that models can efficiently learn the semantic information from such data. Accordingly, graph neural networks (GNNs) indeed achieve impressive success in various fields. Revisiting the...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2023-05 |
---|---|
Hauptverfasser: | , , , , , , , |
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 | Gao, Hang Li, Jiangmeng Qiang, Wenwen Si, Lingyu Su, Xingzhe Wu, Fengge Zheng, Changwen Sun, Fuchun |
description | Benefiting from the injection of human prior knowledge, graphs, as derived discrete data, are semantically dense so that models can efficiently learn the semantic information from such data. Accordingly, graph neural networks (GNNs) indeed achieve impressive success in various fields. Revisiting the GNN learning paradigms, we discover that the relationship between human expertise and the knowledge modeled by GNNs still confuses researchers. To this end, we introduce motivating experiments and derive an empirical observation that the GNNs gradually learn human expertise in general domains. By further observing the ramifications of introducing expertise logic into graph representation learning, we conclude that leading the GNNs to learn human expertise can improve the model performance. Hence, we propose a novel graph representation learning method to incorporate human expert knowledge into GNN models. The proposed method ensures that the GNN model can not only acquire the expertise held by human experts but also engage in end-to-end learning from datasets. Plentiful experiments on the crafted and real-world domains support the consistent effectiveness of the proposed method. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2768578969</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2768578969</sourcerecordid><originalsourceid>FETCH-proquest_journals_27685789693</originalsourceid><addsrcrecordid>eNqNi0sKwjAUAIMgWLR3eOC6UFP7W0qpH-hCxIW7EuprTalJfEnF46vgAVzNYmYmzONRtAqyNecz5lvbh2HIk5THceSxy0E50texkaqD8mWQnLQIle5kA1I5DTsS5gYnNIQWlRNOagUVClLfpSV9hw0UYrRigCOSNdg4-cQFm7ZisOj_OGfLbXku9oEh_RjRurrXI6mPqnmaZHGa5Uke_Ve9AcecQlc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2768578969</pqid></control><display><type>article</type><title>Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective</title><source>Free E- Journals</source><creator>Gao, Hang ; Li, Jiangmeng ; Qiang, Wenwen ; Si, Lingyu ; Su, Xingzhe ; Wu, Fengge ; Zheng, Changwen ; Sun, Fuchun</creator><creatorcontrib>Gao, Hang ; Li, Jiangmeng ; Qiang, Wenwen ; Si, Lingyu ; Su, Xingzhe ; Wu, Fengge ; Zheng, Changwen ; Sun, Fuchun</creatorcontrib><description>Benefiting from the injection of human prior knowledge, graphs, as derived discrete data, are semantically dense so that models can efficiently learn the semantic information from such data. Accordingly, graph neural networks (GNNs) indeed achieve impressive success in various fields. Revisiting the GNN learning paradigms, we discover that the relationship between human expertise and the knowledge modeled by GNNs still confuses researchers. To this end, we introduce motivating experiments and derive an empirical observation that the GNNs gradually learn human expertise in general domains. By further observing the ramifications of introducing expertise logic into graph representation learning, we conclude that leading the GNNs to learn human expertise can improve the model performance. Hence, we propose a novel graph representation learning method to incorporate human expert knowledge into GNN models. The proposed method ensures that the GNN model can not only acquire the expertise held by human experts but also engage in end-to-end learning from datasets. Plentiful experiments on the crafted and real-world domains support the consistent effectiveness of the proposed method.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Cognitive tasks ; Domains ; Graph neural networks ; Graph representations ; Graphical representations ; Learning ; Logic ; Optimization</subject><ispartof>arXiv.org, 2023-05</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>780,784</link.rule.ids></links><search><creatorcontrib>Gao, Hang</creatorcontrib><creatorcontrib>Li, Jiangmeng</creatorcontrib><creatorcontrib>Qiang, Wenwen</creatorcontrib><creatorcontrib>Si, Lingyu</creatorcontrib><creatorcontrib>Su, Xingzhe</creatorcontrib><creatorcontrib>Wu, Fengge</creatorcontrib><creatorcontrib>Zheng, Changwen</creatorcontrib><creatorcontrib>Sun, Fuchun</creatorcontrib><title>Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective</title><title>arXiv.org</title><description>Benefiting from the injection of human prior knowledge, graphs, as derived discrete data, are semantically dense so that models can efficiently learn the semantic information from such data. Accordingly, graph neural networks (GNNs) indeed achieve impressive success in various fields. Revisiting the GNN learning paradigms, we discover that the relationship between human expertise and the knowledge modeled by GNNs still confuses researchers. To this end, we introduce motivating experiments and derive an empirical observation that the GNNs gradually learn human expertise in general domains. By further observing the ramifications of introducing expertise logic into graph representation learning, we conclude that leading the GNNs to learn human expertise can improve the model performance. Hence, we propose a novel graph representation learning method to incorporate human expert knowledge into GNN models. The proposed method ensures that the GNN model can not only acquire the expertise held by human experts but also engage in end-to-end learning from datasets. Plentiful experiments on the crafted and real-world domains support the consistent effectiveness of the proposed method.</description><subject>Cognitive tasks</subject><subject>Domains</subject><subject>Graph neural networks</subject><subject>Graph representations</subject><subject>Graphical representations</subject><subject>Learning</subject><subject>Logic</subject><subject>Optimization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNi0sKwjAUAIMgWLR3eOC6UFP7W0qpH-hCxIW7EuprTalJfEnF46vgAVzNYmYmzONRtAqyNecz5lvbh2HIk5THceSxy0E50texkaqD8mWQnLQIle5kA1I5DTsS5gYnNIQWlRNOagUVClLfpSV9hw0UYrRigCOSNdg4-cQFm7ZisOj_OGfLbXku9oEh_RjRurrXI6mPqnmaZHGa5Uke_Ve9AcecQlc</recordid><startdate>20230524</startdate><enddate>20230524</enddate><creator>Gao, Hang</creator><creator>Li, Jiangmeng</creator><creator>Qiang, Wenwen</creator><creator>Si, Lingyu</creator><creator>Su, Xingzhe</creator><creator>Wu, Fengge</creator><creator>Zheng, Changwen</creator><creator>Sun, Fuchun</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>20230524</creationdate><title>Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective</title><author>Gao, Hang ; Li, Jiangmeng ; Qiang, Wenwen ; Si, Lingyu ; Su, Xingzhe ; Wu, Fengge ; Zheng, Changwen ; Sun, Fuchun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27685789693</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Cognitive tasks</topic><topic>Domains</topic><topic>Graph neural networks</topic><topic>Graph representations</topic><topic>Graphical representations</topic><topic>Learning</topic><topic>Logic</topic><topic>Optimization</topic><toplevel>online_resources</toplevel><creatorcontrib>Gao, Hang</creatorcontrib><creatorcontrib>Li, Jiangmeng</creatorcontrib><creatorcontrib>Qiang, Wenwen</creatorcontrib><creatorcontrib>Si, Lingyu</creatorcontrib><creatorcontrib>Su, Xingzhe</creatorcontrib><creatorcontrib>Wu, Fengge</creatorcontrib><creatorcontrib>Zheng, Changwen</creatorcontrib><creatorcontrib>Sun, Fuchun</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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>Gao, Hang</au><au>Li, Jiangmeng</au><au>Qiang, Wenwen</au><au>Si, Lingyu</au><au>Su, Xingzhe</au><au>Wu, Fengge</au><au>Zheng, Changwen</au><au>Sun, Fuchun</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective</atitle><jtitle>arXiv.org</jtitle><date>2023-05-24</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>Benefiting from the injection of human prior knowledge, graphs, as derived discrete data, are semantically dense so that models can efficiently learn the semantic information from such data. Accordingly, graph neural networks (GNNs) indeed achieve impressive success in various fields. Revisiting the GNN learning paradigms, we discover that the relationship between human expertise and the knowledge modeled by GNNs still confuses researchers. To this end, we introduce motivating experiments and derive an empirical observation that the GNNs gradually learn human expertise in general domains. By further observing the ramifications of introducing expertise logic into graph representation learning, we conclude that leading the GNNs to learn human expertise can improve the model performance. Hence, we propose a novel graph representation learning method to incorporate human expert knowledge into GNN models. The proposed method ensures that the GNN model can not only acquire the expertise held by human experts but also engage in end-to-end learning from datasets. Plentiful experiments on the crafted and real-world domains support the consistent effectiveness of the proposed method.</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, 2023-05 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2768578969 |
source | Free E- Journals |
subjects | Cognitive tasks Domains Graph neural networks Graph representations Graphical representations Learning Logic Optimization |
title | Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective |
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%3A13%3A52IST&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=Introducing%20Expertise%20Logic%20into%20Graph%20Representation%20Learning%20from%20A%20Causal%20Perspective&rft.jtitle=arXiv.org&rft.au=Gao,%20Hang&rft.date=2023-05-24&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2768578969%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2768578969&rft_id=info:pmid/&rfr_iscdi=true |