基于上下文感知特征交互的推荐系统

Pengcheng Ma, Qian Gao, Jun Fan
{"title":"基于上下文感知特征交互的推荐系统","authors":"Pengcheng Ma, Qian Gao, Jun Fan","doi":"10.1109/IRC.2020.00092","DOIUrl":null,"url":null,"abstract":"Additional context information has strong support for all kinds of recommendation systems, so context aware recommendation systems have been widely concerned in recent years. The existing mainstream context aware recommendation model adopts the neural network method, which combines the user's long-term and short-term preferences with the input query to carry out personalized product recommendation.Based on the matrix factorization model, this paper proposes a new interaction mode network model, which consists of three modules: context user / item interaction module, attention mechanism module and context environment overall role module. In this model, we use bilinear function to establish the interaction between context and user / item, and add attention mechanism to distinguish the importance of different context information. Finally, we add user score bias and item score bias which are changed by context environment to the traditional matrix factorization method. Combined with the above methods, we set up a matrix factorization recommendation model based on context aware feature interaction, named “feature interactive network model” (FINM). Through experiments on data sets, it is shown that the algorithm proposed in this paper is superior to the general recommendation algorithm.","PeriodicalId":232817,"journal":{"name":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","volume":"227 2","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Context Aware Feature Interaction based Recommendation System\",\"authors\":\"Pengcheng Ma, Qian Gao, Jun Fan\",\"doi\":\"10.1109/IRC.2020.00092\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Additional context information has strong support for all kinds of recommendation systems, so context aware recommendation systems have been widely concerned in recent years. The existing mainstream context aware recommendation model adopts the neural network method, which combines the user's long-term and short-term preferences with the input query to carry out personalized product recommendation.Based on the matrix factorization model, this paper proposes a new interaction mode network model, which consists of three modules: context user / item interaction module, attention mechanism module and context environment overall role module. In this model, we use bilinear function to establish the interaction between context and user / item, and add attention mechanism to distinguish the importance of different context information. Finally, we add user score bias and item score bias which are changed by context environment to the traditional matrix factorization method. Combined with the above methods, we set up a matrix factorization recommendation model based on context aware feature interaction, named “feature interactive network model” (FINM). Through experiments on data sets, it is shown that the algorithm proposed in this paper is superior to the general recommendation algorithm.\",\"PeriodicalId\":232817,\"journal\":{\"name\":\"2020 Fourth IEEE International Conference on Robotic Computing (IRC)\",\"volume\":\"227 2\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Fourth IEEE International Conference on Robotic Computing (IRC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IRC.2020.00092\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Fourth IEEE International Conference on Robotic Computing (IRC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IRC.2020.00092","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

附加上下文信息对各种推荐系统都有很强的支持作用,因此上下文感知推荐系统近年来受到了广泛关注。现有主流的上下文感知推荐模型采用神经网络方法,将用户的长期和短期偏好与输入查询相结合,进行个性化的产品推荐。基于矩阵分解模型,提出了一种新的交互模式网络模型,该模型由三个模块组成:情境用户/物品交互模块、注意机制模块和情境环境整体角色模块。在该模型中,我们使用双线性函数来建立情境与用户/物品之间的交互关系,并增加注意机制来区分不同情境信息的重要性。最后,我们在传统的矩阵分解方法中加入了用户分数偏差和项目分数偏差,这些偏差会随着上下文环境的变化而变化。结合上述方法,我们建立了基于上下文感知特征交互的矩阵分解推荐模型,称为“特征交互网络模型”(FINM)。通过对数据集的实验,表明本文提出的算法优于一般推荐算法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Context Aware Feature Interaction based Recommendation System
Additional context information has strong support for all kinds of recommendation systems, so context aware recommendation systems have been widely concerned in recent years. The existing mainstream context aware recommendation model adopts the neural network method, which combines the user's long-term and short-term preferences with the input query to carry out personalized product recommendation.Based on the matrix factorization model, this paper proposes a new interaction mode network model, which consists of three modules: context user / item interaction module, attention mechanism module and context environment overall role module. In this model, we use bilinear function to establish the interaction between context and user / item, and add attention mechanism to distinguish the importance of different context information. Finally, we add user score bias and item score bias which are changed by context environment to the traditional matrix factorization method. Combined with the above methods, we set up a matrix factorization recommendation model based on context aware feature interaction, named “feature interactive network model” (FINM). Through experiments on data sets, it is shown that the algorithm proposed in this paper is superior to the general recommendation algorithm.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信