Enhancing Graph Contrastive Learning with Node Similarity

Graph Neural Networks (GNNs) have achieved great success in learning graph representations and thus facilitating various graph-related tasks. However, most GNN methods adopt a supervised learning setting, which is not always feasible in real-world applications due to the difficulty to obtain labeled...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2022-08
Hauptverfasser: Chi, Hongliang, Yao, Ma
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 Chi, Hongliang
Yao, Ma
description Graph Neural Networks (GNNs) have achieved great success in learning graph representations and thus facilitating various graph-related tasks. However, most GNN methods adopt a supervised learning setting, which is not always feasible in real-world applications due to the difficulty to obtain labeled data. Hence, graph self-supervised learning has been attracting increasing attention. Graph contrastive learning (GCL) is a representative framework for self-supervised learning. In general, GCL learns node representations by contrasting semantically similar nodes (positive samples) and dissimilar nodes (negative samples) with anchor nodes. Without access to labels, positive samples are typically generated by data augmentation, and negative samples are uniformly sampled from the entire graph, which leads to a sub-optimal objective. Specifically, data augmentation naturally limits the number of positive samples that involve in the process (typically only one positive sample is adopted). On the other hand, the random sampling process would inevitably select false-negative samples (samples sharing the same semantics with the anchor). These issues limit the learning capability of GCL. In this work, we propose an enhanced objective that addresses the aforementioned issues. We first introduce an unachievable ideal objective that contains all positive samples and no false-negative samples. This ideal objective is then transformed into a probabilistic form based on the distributions for sampling positive and negative samples. We then model these distributions with node similarity and derive the enhanced objective. Comprehensive experiments on various datasets demonstrate the effectiveness of the proposed enhanced objective under different settings.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2702669169</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2702669169</sourcerecordid><originalsourceid>FETCH-proquest_journals_27026691693</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdM3LSMxLzsxLV3AvSizIUHDOzyspSiwuySxLVfBJTSzKA0mVZ5ZkKPjlp6QqBGfmZuYkFmWWVPIwsKYl5hSn8kJpbgZlN9cQZw_dgqL8wtLU4pL4rPzSojygVLyROdBCM0tDM0tj4lQBAIJoNoY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2702669169</pqid></control><display><type>article</type><title>Enhancing Graph Contrastive Learning with Node Similarity</title><source>Free E- Journals</source><creator>Chi, Hongliang ; Yao, Ma</creator><creatorcontrib>Chi, Hongliang ; Yao, Ma</creatorcontrib><description>Graph Neural Networks (GNNs) have achieved great success in learning graph representations and thus facilitating various graph-related tasks. However, most GNN methods adopt a supervised learning setting, which is not always feasible in real-world applications due to the difficulty to obtain labeled data. Hence, graph self-supervised learning has been attracting increasing attention. Graph contrastive learning (GCL) is a representative framework for self-supervised learning. In general, GCL learns node representations by contrasting semantically similar nodes (positive samples) and dissimilar nodes (negative samples) with anchor nodes. Without access to labels, positive samples are typically generated by data augmentation, and negative samples are uniformly sampled from the entire graph, which leads to a sub-optimal objective. Specifically, data augmentation naturally limits the number of positive samples that involve in the process (typically only one positive sample is adopted). On the other hand, the random sampling process would inevitably select false-negative samples (samples sharing the same semantics with the anchor). These issues limit the learning capability of GCL. In this work, we propose an enhanced objective that addresses the aforementioned issues. We first introduce an unachievable ideal objective that contains all positive samples and no false-negative samples. This ideal objective is then transformed into a probabilistic form based on the distributions for sampling positive and negative samples. We then model these distributions with node similarity and derive the enhanced objective. Comprehensive experiments on various datasets demonstrate the effectiveness of the proposed enhanced objective under different settings.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Data augmentation ; Graph neural networks ; Graph representations ; Graphical representations ; Nodes ; Random sampling ; Semantics ; Similarity ; Supervised learning</subject><ispartof>arXiv.org, 2022-08</ispartof><rights>2022. 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>776,780</link.rule.ids></links><search><creatorcontrib>Chi, Hongliang</creatorcontrib><creatorcontrib>Yao, Ma</creatorcontrib><title>Enhancing Graph Contrastive Learning with Node Similarity</title><title>arXiv.org</title><description>Graph Neural Networks (GNNs) have achieved great success in learning graph representations and thus facilitating various graph-related tasks. However, most GNN methods adopt a supervised learning setting, which is not always feasible in real-world applications due to the difficulty to obtain labeled data. Hence, graph self-supervised learning has been attracting increasing attention. Graph contrastive learning (GCL) is a representative framework for self-supervised learning. In general, GCL learns node representations by contrasting semantically similar nodes (positive samples) and dissimilar nodes (negative samples) with anchor nodes. Without access to labels, positive samples are typically generated by data augmentation, and negative samples are uniformly sampled from the entire graph, which leads to a sub-optimal objective. Specifically, data augmentation naturally limits the number of positive samples that involve in the process (typically only one positive sample is adopted). On the other hand, the random sampling process would inevitably select false-negative samples (samples sharing the same semantics with the anchor). These issues limit the learning capability of GCL. In this work, we propose an enhanced objective that addresses the aforementioned issues. We first introduce an unachievable ideal objective that contains all positive samples and no false-negative samples. This ideal objective is then transformed into a probabilistic form based on the distributions for sampling positive and negative samples. We then model these distributions with node similarity and derive the enhanced objective. Comprehensive experiments on various datasets demonstrate the effectiveness of the proposed enhanced objective under different settings.</description><subject>Data augmentation</subject><subject>Graph neural networks</subject><subject>Graph representations</subject><subject>Graphical representations</subject><subject>Nodes</subject><subject>Random sampling</subject><subject>Semantics</subject><subject>Similarity</subject><subject>Supervised learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwdM3LSMxLzsxLV3AvSizIUHDOzyspSiwuySxLVfBJTSzKA0mVZ5ZkKPjlp6QqBGfmZuYkFmWWVPIwsKYl5hSn8kJpbgZlN9cQZw_dgqL8wtLU4pL4rPzSojygVLyROdBCM0tDM0tj4lQBAIJoNoY</recordid><startdate>20220813</startdate><enddate>20220813</enddate><creator>Chi, Hongliang</creator><creator>Yao, Ma</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>20220813</creationdate><title>Enhancing Graph Contrastive Learning with Node Similarity</title><author>Chi, Hongliang ; Yao, Ma</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27026691693</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Data augmentation</topic><topic>Graph neural networks</topic><topic>Graph representations</topic><topic>Graphical representations</topic><topic>Nodes</topic><topic>Random sampling</topic><topic>Semantics</topic><topic>Similarity</topic><topic>Supervised learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Chi, Hongliang</creatorcontrib><creatorcontrib>Yao, Ma</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>Chi, Hongliang</au><au>Yao, Ma</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Enhancing Graph Contrastive Learning with Node Similarity</atitle><jtitle>arXiv.org</jtitle><date>2022-08-13</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Graph Neural Networks (GNNs) have achieved great success in learning graph representations and thus facilitating various graph-related tasks. However, most GNN methods adopt a supervised learning setting, which is not always feasible in real-world applications due to the difficulty to obtain labeled data. Hence, graph self-supervised learning has been attracting increasing attention. Graph contrastive learning (GCL) is a representative framework for self-supervised learning. In general, GCL learns node representations by contrasting semantically similar nodes (positive samples) and dissimilar nodes (negative samples) with anchor nodes. Without access to labels, positive samples are typically generated by data augmentation, and negative samples are uniformly sampled from the entire graph, which leads to a sub-optimal objective. Specifically, data augmentation naturally limits the number of positive samples that involve in the process (typically only one positive sample is adopted). On the other hand, the random sampling process would inevitably select false-negative samples (samples sharing the same semantics with the anchor). These issues limit the learning capability of GCL. In this work, we propose an enhanced objective that addresses the aforementioned issues. We first introduce an unachievable ideal objective that contains all positive samples and no false-negative samples. This ideal objective is then transformed into a probabilistic form based on the distributions for sampling positive and negative samples. We then model these distributions with node similarity and derive the enhanced objective. Comprehensive experiments on various datasets demonstrate the effectiveness of the proposed enhanced objective under different settings.</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, 2022-08
issn 2331-8422
language eng
recordid cdi_proquest_journals_2702669169
source Free E- Journals
subjects Data augmentation
Graph neural networks
Graph representations
Graphical representations
Nodes
Random sampling
Semantics
Similarity
Supervised learning
title Enhancing Graph Contrastive Learning with Node Similarity
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T17%3A38%3A01IST&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=Enhancing%20Graph%20Contrastive%20Learning%20with%20Node%20Similarity&rft.jtitle=arXiv.org&rft.au=Chi,%20Hongliang&rft.date=2022-08-13&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2702669169%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2702669169&rft_id=info:pmid/&rfr_iscdi=true