Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation

Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wei, Yuecen, Fu, Xingcheng, Sun, Qingyun, Peng, Hao, Wu, Jia, Wang, Jinyan, Li, Xianxian
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 Wei, Yuecen
Fu, Xingcheng
Sun, Qingyun
Peng, Hao
Wu, Jia
Wang, Jinyan
Li, Xianxian
description Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning result, especially sensitive information. However, the privacy-preserving methods on homogeneous graphs only preserve the same type of node attributes or relationships, which cannot effectively work on heterogeneous graphs due to the complexity. To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology. In particular, we first define a new attack scheme to reveal privacy leakage in the heterogeneous graphs. Specifically, we design a two-stage pipeline framework, which includes the privacy-preserving feature encoder and the heterogeneous link reconstructor with gradients perturbation based on differential privacy to tolerate data diversity and against the attack. To better control the noise and promote model performance, we utilize a bi-level optimization pattern to allocate a suitable privacy budget for the above two modules. Our experiments on four public benchmarks show that the HeteDP method is equipped to resist heterogeneous graph privacy leakage with admirable model generalization.
doi_str_mv 10.48550/arxiv.2210.00538
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_00538</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_00538</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-b9b1ebadc5c71ab6c941737cbc37caaab12640f04f0647c174d6bd9548f83cf63</originalsourceid><addsrcrecordid>eNotj71OwzAURr0woMIDMJEXSLHjv2REFTRIFVSoe3TtXBeLJq5u0kDfnlBYviN9w5EOY3eCL1WpNX8A-o7Tsijmg3Mty2tW1zgipT32mE5DtiY4fmSveCI4zBi_En1mIVG2pTiBP-dbwgFpiv0-e0efug77FsaY-ht2FeAw4O0_F2z3_LRb1fnmbf2yetzkYGyZu8oJdNB67a0AZ3ylhJXWOz8PADhRGMUDV4EbZb2wqjWurbQqQyl9MHLB7v-0l5TmSLEDOje_Sc0lSf4ATtlIAA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation</title><source>arXiv.org</source><creator>Wei, Yuecen ; Fu, Xingcheng ; Sun, Qingyun ; Peng, Hao ; Wu, Jia ; Wang, Jinyan ; Li, Xianxian</creator><creatorcontrib>Wei, Yuecen ; Fu, Xingcheng ; Sun, Qingyun ; Peng, Hao ; Wu, Jia ; Wang, Jinyan ; Li, Xianxian</creatorcontrib><description>Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning result, especially sensitive information. However, the privacy-preserving methods on homogeneous graphs only preserve the same type of node attributes or relationships, which cannot effectively work on heterogeneous graphs due to the complexity. To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology. In particular, we first define a new attack scheme to reveal privacy leakage in the heterogeneous graphs. Specifically, we design a two-stage pipeline framework, which includes the privacy-preserving feature encoder and the heterogeneous link reconstructor with gradients perturbation based on differential privacy to tolerate data diversity and against the attack. To better control the noise and promote model performance, we utilize a bi-level optimization pattern to allocate a suitable privacy budget for the above two modules. Our experiments on four public benchmarks show that the HeteDP method is equipped to resist heterogeneous graph privacy leakage with admirable model generalization.</description><identifier>DOI: 10.48550/arxiv.2210.00538</identifier><language>eng</language><subject>Computer Science - Cryptography and Security ; Computer Science - Learning</subject><creationdate>2022-10</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2210.00538$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.00538$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Wei, Yuecen</creatorcontrib><creatorcontrib>Fu, Xingcheng</creatorcontrib><creatorcontrib>Sun, Qingyun</creatorcontrib><creatorcontrib>Peng, Hao</creatorcontrib><creatorcontrib>Wu, Jia</creatorcontrib><creatorcontrib>Wang, Jinyan</creatorcontrib><creatorcontrib>Li, Xianxian</creatorcontrib><title>Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation</title><description>Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning result, especially sensitive information. However, the privacy-preserving methods on homogeneous graphs only preserve the same type of node attributes or relationships, which cannot effectively work on heterogeneous graphs due to the complexity. To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology. In particular, we first define a new attack scheme to reveal privacy leakage in the heterogeneous graphs. Specifically, we design a two-stage pipeline framework, which includes the privacy-preserving feature encoder and the heterogeneous link reconstructor with gradients perturbation based on differential privacy to tolerate data diversity and against the attack. To better control the noise and promote model performance, we utilize a bi-level optimization pattern to allocate a suitable privacy budget for the above two modules. Our experiments on four public benchmarks show that the HeteDP method is equipped to resist heterogeneous graph privacy leakage with admirable model generalization.</description><subject>Computer Science - Cryptography and Security</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71OwzAURr0woMIDMJEXSLHjv2REFTRIFVSoe3TtXBeLJq5u0kDfnlBYviN9w5EOY3eCL1WpNX8A-o7Tsijmg3Mty2tW1zgipT32mE5DtiY4fmSveCI4zBi_En1mIVG2pTiBP-dbwgFpiv0-e0efug77FsaY-ht2FeAw4O0_F2z3_LRb1fnmbf2yetzkYGyZu8oJdNB67a0AZ3ylhJXWOz8PADhRGMUDV4EbZb2wqjWurbQqQyl9MHLB7v-0l5TmSLEDOje_Sc0lSf4ATtlIAA</recordid><startdate>20221002</startdate><enddate>20221002</enddate><creator>Wei, Yuecen</creator><creator>Fu, Xingcheng</creator><creator>Sun, Qingyun</creator><creator>Peng, Hao</creator><creator>Wu, Jia</creator><creator>Wang, Jinyan</creator><creator>Li, Xianxian</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221002</creationdate><title>Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation</title><author>Wei, Yuecen ; Fu, Xingcheng ; Sun, Qingyun ; Peng, Hao ; Wu, Jia ; Wang, Jinyan ; Li, Xianxian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-b9b1ebadc5c71ab6c941737cbc37caaab12640f04f0647c174d6bd9548f83cf63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Cryptography and Security</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Wei, Yuecen</creatorcontrib><creatorcontrib>Fu, Xingcheng</creatorcontrib><creatorcontrib>Sun, Qingyun</creatorcontrib><creatorcontrib>Peng, Hao</creatorcontrib><creatorcontrib>Wu, Jia</creatorcontrib><creatorcontrib>Wang, Jinyan</creatorcontrib><creatorcontrib>Li, Xianxian</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Wei, Yuecen</au><au>Fu, Xingcheng</au><au>Sun, Qingyun</au><au>Peng, Hao</au><au>Wu, Jia</au><au>Wang, Jinyan</au><au>Li, Xianxian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation</atitle><date>2022-10-02</date><risdate>2022</risdate><abstract>Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning result, especially sensitive information. However, the privacy-preserving methods on homogeneous graphs only preserve the same type of node attributes or relationships, which cannot effectively work on heterogeneous graphs due to the complexity. To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology. In particular, we first define a new attack scheme to reveal privacy leakage in the heterogeneous graphs. Specifically, we design a two-stage pipeline framework, which includes the privacy-preserving feature encoder and the heterogeneous link reconstructor with gradients perturbation based on differential privacy to tolerate data diversity and against the attack. To better control the noise and promote model performance, we utilize a bi-level optimization pattern to allocate a suitable privacy budget for the above two modules. Our experiments on four public benchmarks show that the HeteDP method is equipped to resist heterogeneous graph privacy leakage with admirable model generalization.</abstract><doi>10.48550/arxiv.2210.00538</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.00538
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_00538
source arXiv.org
subjects Computer Science - Cryptography and Security
Computer Science - Learning
title Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T00%3A02%3A55IST&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=Heterogeneous%20Graph%20Neural%20Network%20for%20Privacy-Preserving%20Recommendation&rft.au=Wei,%20Yuecen&rft.date=2022-10-02&rft_id=info:doi/10.48550/arxiv.2210.00538&rft_dat=%3Carxiv_GOX%3E2210_00538%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