自监督混合图神经网络的会话推荐模型
TP391; 基于会话的推荐旨在利用匿名会话预测用户行为.现有基于图神经网络(GNN)的会话推荐算法大多仅针对当前会话提取用户偏好,却忽略了来自其他会话的高阶多元关系从而影响推荐精度.此外,由于会话推荐所采用的短时交互序列包含的信息非常有限,使其更容易受到数据稀疏性的影响.针对上述问题,提出了自监督混合图神经网络会话推荐模型(SHGN).该模型首先通过将原始数据构建为三个视图来描述会话与物品关系,然后通过多头图注意力网络捕获会话内部物品的低阶转换信息,提出了残差图卷积网络捕获物品和会话的高阶转换信息;最后融合自监督学习(SSL)作为辅助任务,通过最大化不同通道学习到的会话嵌入的互信息,对原始数...
Saved in:
| Published in | 计算机科学与探索 Vol. 18; no. 4; pp. 1021 - 1031 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
江苏省媒体设计与软件技术重点实验室,江苏 无锡 214122
01.04.2024
江南大学 人工智能与计算机学院,江苏 无锡 214122%江南大学 人工智能与计算机学院,江苏 无锡 214122 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1673-9418 |
| DOI | 10.3778/j.issn.1673-9418.2212043 |
Cover
| Abstract | TP391; 基于会话的推荐旨在利用匿名会话预测用户行为.现有基于图神经网络(GNN)的会话推荐算法大多仅针对当前会话提取用户偏好,却忽略了来自其他会话的高阶多元关系从而影响推荐精度.此外,由于会话推荐所采用的短时交互序列包含的信息非常有限,使其更容易受到数据稀疏性的影响.针对上述问题,提出了自监督混合图神经网络会话推荐模型(SHGN).该模型首先通过将原始数据构建为三个视图来描述会话与物品关系,然后通过多头图注意力网络捕获会话内部物品的低阶转换信息,提出了残差图卷积网络捕获物品和会话的高阶转换信息;最后融合自监督学习(SSL)作为辅助任务,通过最大化不同通道学习到的会话嵌入的互信息,对原始数据进行数据增强从而提升推荐性能.为了验证该方法的有效性,在Tmall、Diginetica、Now-playing、Yoochoose四个基准数据集上与SR-GNN、GCE-GNN、DHCN等主流基线模型进行了对比实验,实验结果在P@20、MRR@20等性能指标上均取得了一定提升. |
|---|---|
| AbstractList | TP391; 基于会话的推荐旨在利用匿名会话预测用户行为.现有基于图神经网络(GNN)的会话推荐算法大多仅针对当前会话提取用户偏好,却忽略了来自其他会话的高阶多元关系从而影响推荐精度.此外,由于会话推荐所采用的短时交互序列包含的信息非常有限,使其更容易受到数据稀疏性的影响.针对上述问题,提出了自监督混合图神经网络会话推荐模型(SHGN).该模型首先通过将原始数据构建为三个视图来描述会话与物品关系,然后通过多头图注意力网络捕获会话内部物品的低阶转换信息,提出了残差图卷积网络捕获物品和会话的高阶转换信息;最后融合自监督学习(SSL)作为辅助任务,通过最大化不同通道学习到的会话嵌入的互信息,对原始数据进行数据增强从而提升推荐性能.为了验证该方法的有效性,在Tmall、Diginetica、Now-playing、Yoochoose四个基准数据集上与SR-GNN、GCE-GNN、DHCN等主流基线模型进行了对比实验,实验结果在P@20、MRR@20等性能指标上均取得了一定提升. |
| Abstract_FL | Session-based recommendation aims to predict user actions based on anonymous sessions.Most of the ex-isting session recommendation algorithms based on graph neural network(GNN)only extract user preferences for the current session,but ignore the high-order multivariate relationships from other sessions,which affects the recom-mendation accuracy.Moreover,session-based recommendation suffers more from the problem of data sparsity due to the very limited short-term interactions.To solve the above problems,this paper proposes a model named self-supervised hybrid graph neural network(SHGN)for session-based recommendation.Firstly,the model describes the relationship between sessions and objects by constructing the original data into three views.Next,a graph attention network is used to capture the low-order transitions information of items within a session,and then a residual graph convolutional network is proposed to mine the high-order transitions information of items and sessions.Finally,self-supervised learning(SSL)is integrated as an auxiliary task.By maximizing the mutual information of session em-beddings learnt from different views,data augmentation is performed to improve the recommendation performance.In order to verify the effectiveness of the proposed method,comparative experiments with mainstream baseline models such as SR-GNN,GCE-GNN and DHCN are carried out on four benchmark datasets of Tmall,Diginetica,Nowplay-ing and Yoochoose,and the results are improved in P@20,MRR@20 and other performance indices. |
| Author | 章淯淞 刘渊 夏鸿斌 |
| AuthorAffiliation | 江南大学 人工智能与计算机学院,江苏 无锡 214122%江南大学 人工智能与计算机学院,江苏 无锡 214122;江苏省媒体设计与软件技术重点实验室,江苏 无锡 214122 |
| AuthorAffiliation_xml | – name: 江南大学 人工智能与计算机学院,江苏 无锡 214122%江南大学 人工智能与计算机学院,江苏 无锡 214122;江苏省媒体设计与软件技术重点实验室,江苏 无锡 214122 |
| Author_FL | LIU Yuan XIA Hongbin ZHANG Yusong |
| Author_FL_xml | – sequence: 1 fullname: ZHANG Yusong – sequence: 2 fullname: XIA Hongbin – sequence: 3 fullname: LIU Yuan |
| Author_xml | – sequence: 1 fullname: 章淯淞 – sequence: 2 fullname: 夏鸿斌 – sequence: 3 fullname: 刘渊 |
| BookMark | eNo9jT1LAzEchzNUsNZ-B1eHO_PyT5OMUnyDQhedS85LpKekYBR1FxREbdfWFkSE4uLYoeqn8S73MSwoTr-HZ3h-K6jies4gtEZwzISQG1nc9d7FpCFYpIDImFJCMbAKqv67ZVT3vptgDkCJaMgqYuXNWxgNwvilmM3y_m0--gqvkzB_DJ-DMH8Kw-vvj2H5Pi4epuV9v5g-55O7VbRk9Yk39b-toYPtrf3mbtRq7-w1N1uRJxgg4lqaVFAljSRKcKsYcCmJkSlwLQ5BqKRBQZkkoZpCarlKF2CIFamwIAyrofXf7oV2VrujTtY7P3WLx07ms-PLqzNPMQUMmAD7AT-yXWQ |
| 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.1673-9418.2212043 |
| 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 Hybrid Graph Neural Network for Session-Based Recommendation |
| EndPage | 1031 |
| ExternalDocumentID | jsjkxyts202404014 |
| GroupedDBID | 2B. 4A8 92I 93N ALMA_UNASSIGNED_HOLDINGS M~E PSX TCJ |
| ID | FETCH-LOGICAL-s1044-5a8ed7298e81975f9345881e8d45a7c479b6249ebb2a24df59d2a2e1f7d7f47e3 |
| ISSN | 1673-9418 |
| IngestDate | Thu May 29 04:00:18 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | 自监督学习 图神经网络 多视图建模 会话推荐 session-based recommendation self-supervised learning graph neural network multi-view modeling |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1044-5a8ed7298e81975f9345881e8d45a7c479b6249ebb2a24df59d2a2e1f7d7f47e3 |
| PageCount | 11 |
| ParticipantIDs | wanfang_journals_jsjkxyts202404014 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-04-01 |
| PublicationDateYYYYMMDD | 2024-04-01 |
| PublicationDate_xml | – month: 04 year: 2024 text: 2024-04-01 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 | 江苏省媒体设计与软件技术重点实验室,江苏 无锡 214122 江南大学 人工智能与计算机学院,江苏 无锡 214122%江南大学 人工智能与计算机学院,江苏 无锡 214122 |
| Publisher_xml | – name: 江南大学 人工智能与计算机学院,江苏 无锡 214122%江南大学 人工智能与计算机学院,江苏 无锡 214122 – name: 江苏省媒体设计与软件技术重点实验室,江苏 无锡 214122 |
| SSID | ssib054421768 ssib002040941 ssib002423894 ssib051375751 ssib023646573 ssib036438069 ssib002040926 |
| Score | 2.3866735 |
| Snippet | TP391; 基于会话的推荐旨在利用匿名会话预测用户行为.现有基于图神经网络(GNN)的会话推荐算法大多仅针对当前会话提取用户偏好,却忽略了来自其他会话的高阶多元关系从而影... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 1021 |
| Title | 自监督混合图神经网络的会话推荐模型 |
| URI | https://d.wanfangdata.com.cn/periodical/jsjkxyts202404014 |
| 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: 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/eLvHCXMwnR1Na9RANNR68SKKit8UcU4lNZlMMvOOk22WItRTC72V7CZRKqzibkF78CQoiNpeW1uQIhQvHnuo-mts05_hey_pbrQVqrCEN5M37zOZeTM7L-M4dwMVBplfBG6RArjY4WkXct7kWHS9PC2UzmlpYPZBNDOv7i-EC2Nnthu7lpYHnanuyol5Jf_jVaxDv1KW7D94dkgUKxBG_-IVPYzXU_lYJEbgZN5akWgBsQCfgWlhA5FEItb0S0IBnjCGgVjECeFYhBmIY2HaDEzXzbEGWkzHCqNEokTcIhh52TYRR8omEdYw92kijjVYtD6zSISJmyEvN0z4riYANOEji5jFtpr5hsKi2BGzM0S_5iJZJIXA0aPBjWJhvVpFFKoCIBmhIDnFigGRixkFkGKriYI2AcONkaNtrn_I5rYZemIZyxfQZqWPbIZKmEp2K0Cy7GiPoNaYLD1UfaiWIRySWZGl44gVtbThpLKKZaHRq2haZGGkiIFZJOwxIF6mVdegkrJ1XLZJpqXZRiAAredPSl_5srHG60c6cEHVw9KxQWq0AvO0OjS4yjCvoxc6teOkkTHQ2vDISCymhiymJIYuXvWhrD--O77UX3r8_MWgTzbHnp4Oiz8rceik81FmXyajGA9vQnOOSmX1W7I0BsXDTp8OLIjCUcyMxcB40TCmDv1A03-Bw7JSOGuuUlqPpK525JFK9_6mEOfg9Yq097ARLs5dcM7X87wJW720F52xlUeXnODw9ZdyY63c3D7Y3d1ffbO_8aP8vFXufSi_r5V7H8v1Vz-_rR9-3Tx4v3P4bvVg59P-1tvLznw7mWvNuPWpJW7f95Ryw9TkGU5ZTY7Btg4LCCgZ3M9NpsJUd5WGTiQV5J2OTKXKihAyBHK_0JnmrvGKM9570suvOhNRlppuIDNIs1R5HQ2-9lSeQxgVslCQXXPu1Eou1r1Sf_GY266fBumGc270bt10xgfPlvNbGG0POrfZ278AYUeZwQ |
| 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%87%AA%E7%9B%91%E7%9D%A3%E6%B7%B7%E5%90%88%E5%9B%BE%E7%A5%9E%E7%BB%8F%E7%BD%91%E7%BB%9C%E7%9A%84%E4%BC%9A%E8%AF%9D%E6%8E%A8%E8%8D%90%E6%A8%A1%E5%9E%8B&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%AB%A0%E6%B7%AF%E6%B7%9E&rft.au=%E5%A4%8F%E9%B8%BF%E6%96%8C&rft.au=%E5%88%98%E6%B8%8A&rft.date=2024-04-01&rft.pub=%E6%B1%9F%E8%8B%8F%E7%9C%81%E5%AA%92%E4%BD%93%E8%AE%BE%E8%AE%A1%E4%B8%8E%E8%BD%AF%E4%BB%B6%E6%8A%80%E6%9C%AF%E9%87%8D%E7%82%B9%E5%AE%9E%E9%AA%8C%E5%AE%A4%2C%E6%B1%9F%E8%8B%8F+%E6%97%A0%E9%94%A1+214122&rft.issn=1673-9418&rft.volume=18&rft.issue=4&rft.spage=1021&rft.epage=1031&rft_id=info:doi/10.3778%2Fj.issn.1673-9418.2212043&rft.externalDocID=jsjkxyts202404014 |
| 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 |