融合残差网络的自监督社交推荐算法
TP391; 基于图神经网络的社交推荐算法,通过社交图和交互图的信息来学习用户和项目的嵌入,得到最终的推荐结果.但是现有算法主要利用静态的社交图结构,无法挖掘用户之间潜在的链接关系,同时也没有解决用户与项目交互行为中的噪声问题.提出了一种融合残差网络的自监督社交推荐算法.采用变分超图自编码器对社交网络进行链接预测,得到重构的社交图,以此来挖掘隐藏在用户间的积极链接关系;利用注意力机制为原始社交图和重构后的残差社交图分配不同的注意力系数,得到更加精确的用户表征;为了缓解数据中的噪声问题,构建了自适应的超图全局关系提取器,在该提取器的协作下利用局部嵌入信息和全局嵌入信息创建自监督信号,从而优化局部...
Saved in:
| Published in | 计算机科学与探索 Vol. 18; no. 12; pp. 3175 - 3188 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | Chinese |
| Published |
苏州大学 计算机科学与技术学院,江苏 苏州 215006
01.12.2024
江苏省计算机信息处理技术重点实验室,江苏 苏州 215006 江苏省大数据智能工程实验室,江苏 苏州 215006 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1673-9418 |
| DOI | 10.3778/j.issn.1673-9418.2401006 |
Cover
| Abstract | TP391; 基于图神经网络的社交推荐算法,通过社交图和交互图的信息来学习用户和项目的嵌入,得到最终的推荐结果.但是现有算法主要利用静态的社交图结构,无法挖掘用户之间潜在的链接关系,同时也没有解决用户与项目交互行为中的噪声问题.提出了一种融合残差网络的自监督社交推荐算法.采用变分超图自编码器对社交网络进行链接预测,得到重构的社交图,以此来挖掘隐藏在用户间的积极链接关系;利用注意力机制为原始社交图和重构后的残差社交图分配不同的注意力系数,得到更加精确的用户表征;为了缓解数据中的噪声问题,构建了自适应的超图全局关系提取器,在该提取器的协作下利用局部嵌入信息和全局嵌入信息创建自监督信号,从而优化局部的嵌入表示,进而缓解噪声影响.该算法在Ciao、Epinions和Yelp三个数据集上与NGCF、LightGCN、MHCN等基线模型进行对比实验.在Ciao数据集上,Recall@10提升了17.1%～48.5%,NDCG@10提升了1.4%～37.9%;在Epinions数据集上,Recall@10提升了8.3%～56.2%,NDCG@10提升了3.7%～29.8%;在Yelp数据集上,Recall@10提升了9.1%～53.3%,NDCG@10提升了11.2%～66.6%.实验结果表明,该算法相较于基准模型有良好的推荐性能. |
|---|---|
| AbstractList | TP391; 基于图神经网络的社交推荐算法,通过社交图和交互图的信息来学习用户和项目的嵌入,得到最终的推荐结果.但是现有算法主要利用静态的社交图结构,无法挖掘用户之间潜在的链接关系,同时也没有解决用户与项目交互行为中的噪声问题.提出了一种融合残差网络的自监督社交推荐算法.采用变分超图自编码器对社交网络进行链接预测,得到重构的社交图,以此来挖掘隐藏在用户间的积极链接关系;利用注意力机制为原始社交图和重构后的残差社交图分配不同的注意力系数,得到更加精确的用户表征;为了缓解数据中的噪声问题,构建了自适应的超图全局关系提取器,在该提取器的协作下利用局部嵌入信息和全局嵌入信息创建自监督信号,从而优化局部的嵌入表示,进而缓解噪声影响.该算法在Ciao、Epinions和Yelp三个数据集上与NGCF、LightGCN、MHCN等基线模型进行对比实验.在Ciao数据集上,Recall@10提升了17.1%～48.5%,NDCG@10提升了1.4%～37.9%;在Epinions数据集上,Recall@10提升了8.3%～56.2%,NDCG@10提升了3.7%～29.8%;在Yelp数据集上,Recall@10提升了9.1%～53.3%,NDCG@10提升了11.2%～66.6%.实验结果表明,该算法相较于基准模型有良好的推荐性能. |
| Abstract_FL | Social recommendation based on graph neural networks learns the embedded relationships between users and items through the information of social graphs and interaction graphs to get the final recommendation results.However,the existing algorithms mainly utilize the static social graph structure,which is unable to mine the poten-tial linking relationship between users,and at the same time do not solve the noise problem in the user-item interac-tion behavior.Therefore,a self-supervised social recommendation algorithm incorporating residual networks is pro-posed.Firstly,the algorithm employs a variational hypergraph auto-encoder for link prediction in social networks to obtain a reconstructed social graph,which is used to mine the positive link relationships hidden among users.Sec-ondly,an attention mechanism is utilized to assign different attention coefficients to the original and the reconstructed residual social graphs to obtain a more accurate representation of users.Lastly,to alleviate the problem of noise in the data,an adaptive hypergraph global relation extractor is constructed.Self-supervised signals are created using local embedding information and global embedding information in collaboration with this extractor,which optimizes the local embedding representation and thus mitigates the effect of noise.The algorithm is experimentally compared with baseline models such as NGCF,LightGCN,and MHCN on three datasets,Ciao,Epinions and Yelp.On the Ciao dataset,Recall@10 is improved by 17.1%to 48.5%,NDCG@10 is improved by 1.4%to 37.9%;on the Epinions dataset,Recall@10 is improved by 8.3%to 56.2%,NDCG@10 is improved by 3.7%to 29.8%;on the Yelp dataset,Recall@10 is improved by 9.1%to 53.3%,NDCG@10 is improved by 11.2%to 66.6%.Experimental results show that the algorithm has good recommendation performance compared with the benchmark model. |
| Author | 杨哲 王玉洁 |
| AuthorAffiliation | 苏州大学 计算机科学与技术学院,江苏 苏州 215006;江苏省计算机信息处理技术重点实验室,江苏 苏州 215006;江苏省大数据智能工程实验室,江苏 苏州 215006 |
| AuthorAffiliation_xml | – name: 苏州大学 计算机科学与技术学院,江苏 苏州 215006;江苏省计算机信息处理技术重点实验室,江苏 苏州 215006;江苏省大数据智能工程实验室,江苏 苏州 215006 |
| Author_FL | YANG Zhe WANG Yujie |
| Author_FL_xml | – sequence: 1 fullname: WANG Yujie – sequence: 2 fullname: YANG Zhe |
| Author_xml | – sequence: 1 fullname: 王玉洁 – sequence: 2 fullname: 杨哲 |
| BookMark | eNo9jT1LAzEYgDNUsNb-B1eHO98kb5N0lOIXFFx0LpfLRXpKCkZRd0FBKu0ggl-LHcThFgdB0V9jL_czFBSnB57heeZIzQ1cRsgChZhLqZbyuO-9i6mQPGojVTFDoACiRur_bpY0ve9raCEyKoWqE6gehtPReVlcTF-L8DEO73fh5rQ6ew6343D_GCafX2-T8vKpGo5CcV2-XM2TGZvs-az5xwbZXl3Z6qxH3c21jc5yN_IUUEZcGgpGGaEsh7SVsJRyiQhKtlOTpEyjAaOF0ha5zRJqBdMShdFZhpyB4g2y-Ns9SpxN3E4vHxzuu59jL_f57vHJgWfAkDIAyb8Bdd9bfg |
| ClassificationCodes | TP391 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.3778/j.issn.1673-9418.2401006 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitle_FL | Self-Supervised Social Recommendation Algorithm Fusing Residual Networks |
| EndPage | 3188 |
| ExternalDocumentID | jsjkxyts202412007 |
| GroupedDBID | 2B. 4A8 92I 93N ALMA_UNASSIGNED_HOLDINGS M~E PSX TCJ |
| ID | FETCH-LOGICAL-s1047-37d10d8d68f30c5a2c137440879cdac2b4d0db68bf43fea1f62b746dbee432083 |
| ISSN | 1673-9418 |
| IngestDate | Thu May 29 04:00:18 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 12 |
| Keywords | social network 自监督学习 hypergraph graph convolutional neural network 社交网络 推荐系统 超图 self-supervised learning 图卷积神经网络 recommendation system |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1047-37d10d8d68f30c5a2c137440879cdac2b4d0db68bf43fea1f62b746dbee432083 |
| PageCount | 14 |
| ParticipantIDs | wanfang_journals_jsjkxyts202412007 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-12-01 |
| PublicationDateYYYYMMDD | 2024-12-01 |
| PublicationDate_xml | – month: 12 year: 2024 text: 2024-12-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 计算机科学与探索 |
| PublicationTitle_FL | Journal of Frontiers of Computer Science & Technology |
| PublicationYear | 2024 |
| Publisher | 苏州大学 计算机科学与技术学院,江苏 苏州 215006 江苏省计算机信息处理技术重点实验室,江苏 苏州 215006 江苏省大数据智能工程实验室,江苏 苏州 215006 |
| Publisher_xml | – name: 江苏省大数据智能工程实验室,江苏 苏州 215006 – name: 苏州大学 计算机科学与技术学院,江苏 苏州 215006 – name: 江苏省计算机信息处理技术重点实验室,江苏 苏州 215006 |
| SSID | ssib054421768 ssib002040941 ssib002423894 ssib051375751 ssib023646573 ssib036438069 ssib002040926 |
| Score | 2.4066901 |
| Snippet | TP391; 基于图神经网络的社交推荐算法,通过社交图和交互图的信息来学习用户和项目的嵌入,得到最终的推荐结果.但是现有算法主要利用静态的社交图结构,无法挖掘用户之间潜在... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 3175 |
| Title | 融合残差网络的自监督社交推荐算法 |
| URI | https://d.wanfangdata.com.cn/periodical/jsjkxyts202412007 |
| Volume | 18 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVEBS databaseName: Inspec with Full Text issn: 1673-9418 databaseCode: ADMLS dateStart: 20200501 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text omitProxy: false ssIdentifier: ssib002423894 providerName: EBSCOhost – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center) issn: 1673-9418 databaseCode: M~E dateStart: 20070101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://road.issn.org omitProxy: true ssIdentifier: ssib054421768 providerName: ISSN International Centre |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NaxQxFB9qvXgRRcVviphT2XVmks3HMbM7SxHqqYWeLJP5UCqs4G5Be_AkKEilPYjg18UexMNePAiK_jV2Z_8M38vMzs7aClUv4SXzkvdeXib5ZSYfjnM9hTaRRDDJEXFKG8zLaENFsWkkXoK_ddyMC9zvvHyLL62ym2uttbljt2urljYHphlvHbqv5F-8CmngV9wl-xeerQqFBKDBvxCChyE8ko9JKIkKieyQsEWUS6QkIScaUgJMCQTSoSBBhyjPEgFRbSSUJpJhdgk82qYEJY_qEE2R0IwEkB1CjTSULEOipc3VQXGhLV8JfBRQUlxjOUG6yAZPtTfDBtIDK04LK65FNIjjVorE8kspvtWWATFpEZggC8sKQlmxCIWnLNxqL211UBL49W8aPvttfYg1JCCyW9YV1CTqw1C3iWKL_2GGxlUkBbPu1ngUUQot9NvWAo-obqXK4kGlFgEuuS6vjR5cQFNn5YByYHjZrJaMF4MFQrca8IDeVR42qFEhpB3UUEazktEELOZNxM8eGb7R37j38NGgj1XrFYctHPcF53jDx_LjcArPoAdX9eklxtnMPmfAs1V_jXcN8NYU7kKUSpdXcLjlUYG_8ao4YzDhLXajTrQuFtOhSTf-ZJDdPtfLot6dGtJbOeWcLKdoC7p43047c1t3zzju-P32_s6z0fD5_pdh_n03__Y2f_1k_PRT_mY3f_ch3_vx8-ve6MXH8fZOPnw1-vzyrLPaDVfaS43ytpFG3x5XQkXiuYlMuMyoG7ciPwZz8D52oeIkin3DEjcxXJqM0SyNvIz7RjCemDRl1IeZzDlnvne_l553FoSgJopTBWjAMKFcaWKaGcn9LGUmM_SCc620cL3sTfrrB3x28ShMl5wT0_fnsjM_eLCZXgGUPDBXrat_AR2OiIM |
| linkProvider | ISSN International Centre |
| 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%3Ajournal&rft.genre=article&rft.atitle=%E8%9E%8D%E5%90%88%E6%AE%8B%E5%B7%AE%E7%BD%91%E7%BB%9C%E7%9A%84%E8%87%AA%E7%9B%91%E7%9D%A3%E7%A4%BE%E4%BA%A4%E6%8E%A8%E8%8D%90%E7%AE%97%E6%B3%95&rft.jtitle=%E8%AE%A1%E7%AE%97%E6%9C%BA%E7%A7%91%E5%AD%A6%E4%B8%8E%E6%8E%A2%E7%B4%A2&rft.au=%E7%8E%8B%E7%8E%89%E6%B4%81&rft.au=%E6%9D%A8%E5%93%B2&rft.date=2024-12-01&rft.pub=%E8%8B%8F%E5%B7%9E%E5%A4%A7%E5%AD%A6+%E8%AE%A1%E7%AE%97%E6%9C%BA%E7%A7%91%E5%AD%A6%E4%B8%8E%E6%8A%80%E6%9C%AF%E5%AD%A6%E9%99%A2%2C%E6%B1%9F%E8%8B%8F+%E8%8B%8F%E5%B7%9E+215006&rft.issn=1673-9418&rft.volume=18&rft.issue=12&rft.spage=3175&rft.epage=3188&rft_id=info:doi/10.3778%2Fj.issn.1673-9418.2401006&rft.externalDocID=jsjkxyts202412007 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjsjkxyts%2Fjsjkxyts.jpg |