基于评论方面级用户偏好迁移的跨领域推荐算法

计算机科学 ›› 2022, Vol. 49 ›› Issue (9): 41-47.doi: 10.11896/jsjkx.220200131

• 数据库&大数据&数据科学^* • 上一篇下一篇

基于评论方面级用户偏好迁移的跨领域推荐算法

张佳, 董守斌

华南理工大学计算机科学与工程学院广州 510006
中山市华南理工大学现代产业技术研究院广东中山 528437

收稿日期:2022-02-22 修回日期:2022-06-08 出版日期:2022-09-15 发布日期:2022-09-09
通讯作者: 董守斌(sbdong@scut.edu.cn)
作者简介:(cszhangjia@mail.scut.edu.cn)

Cross-domain Recommendation Based on Review Aspect-level User Preference Transfer

ZHANG Jia, DONG Shou-bin

School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,China
Zhongshan Institute of Modern Industrial Technology of SCUT,Zhongshan,Guangdong 528437,China

Received:2022-02-22 Revised:2022-06-08 Online:2022-09-15 Published:2022-09-09
About author:ZHANG Jia,born in 1996,postgra-duate.Her main research interests include recommendation systems and natural language processing.
DONG Shou-bin,born in 1967,Ph.D,professor,Ph.D supervisor.Her main research interests include information retrieval,natural language processing and high-performance computing.

摘要/Abstract

摘要： 为解决推荐系统中数据稀疏造成的用户冷启动问题,文中提出了一种基于方面级用户偏好迁移的跨领域推荐算法(Cross-Domain Recommendation via Review Aspect-Level User Preference Transfer,CAUT),设计了基于两阶段生成对抗网络的用户方面级偏好跨领域迁移结构,通过用户历史评论挖掘用户细粒度方面级偏好。CAUT利用预训练源领域编码器参数对目标领域编码器进行参数初始化,在固定源领域编码器参数的同时引入领域鉴别器,以解决源领域与目标领域数据分布差异的问题,进而可以有效利用源领域的丰富数据,缓解目标领域数据稀疏造成的用户冷启动问题。在亚马逊电商平台真实数据集上进行了实验,结果表明,与最新算法相比,CAUT在用户对商品的评分预测均方根误差(RMSE)指标上有明显的提升,说明CAUT可有效缓解用户冷启动问题。

关键词: 跨领域推荐, 方面级用户偏好, 用户冷启动, 生成对抗网络

Abstract: In order to solve the user cold-start problem caused by data-sparse in recommender system,this paper proposes a cross-domain recommendation algorithm based on aspect-level user preference transfer,named CAUT.CAUT is devised to learn aspect transfer across domains from a two-stage generative adversarial network and extract aspect-level user fine-grained prefe-rence from reviews.The data distribution misalignment between source and target domains is eliminated by fixing source domain encoder parameters and designing a domain discriminator.Then the user cold-start problem caused by data-sparse in the target domain could be alleviated by utilizing source domain data via CAUT.Experiments on real-world datasets show that the proposed CAUT outperforms SOTA models significantly in rating prediction RMSE indicator,suggesting that CAUT can effectively solve the user cold-start problem.

Key words: Cross-domain recommendation, Aspect-level user preference, Cold-start user, Generative adversarial network

中图分类号:

TP391

张佳, 董守斌. 基于评论方面级用户偏好迁移的跨领域推荐算法[J]. 计算机科学, 2022, 49(9): 41-47. https://doi.org/10.11896/jsjkx.220200131

ZHANG Jia, DONG Shou-bin. Cross-domain Recommendation Based on Review Aspect-level User Preference Transfer[J]. Computer Science, 2022, 49(9): 41-47. https://doi.org/10.11896/jsjkx.220200131

参考文献

[1]MAN T,SHEN H,JIN X,et al.Cross-Domain Recommendation:An Embedding and Mapping Approach[C]//Proceedings of IJCAI.Morgan Kaufmann,2017:2464-2470.
[2]WANG X,PENG Z,WANG S,et al.CDLFM:cross-domain reco-mmendation for cold-start users via latent feature mapping[J].Knowledge and Information Systems,2019,62(5):1-28.
[3]HU G,ZHANG Y,YANG Q.CoNet:Collabora-tive Cross Networks for Cross-Domain Recommendation[C]//Proceedings of CIKM.ACM,2018:667-676.
[4]JIN Y,DONG S,CAI Y.RACRec:Review Aw-are Cross-Domain Recommendation for Fully-Cold-Start User[J].IEEE Access,2020,8(3):55032-55041.
[5]WANG C,NIEPERT M,LI H.Recsys-dan:dis-criminative adversarial networks for cross-domain recommender systems[J].IEEE Trans. Neural Netw.Learn. Syst.,2019,31(8):2731-2740.
[6]ZHU F,CHEN C,WANG Y,et al.DTCDR:A Framework for Dual-Target Cross-Domain Recom-mendation[C]//Proceedings of CIKM.ACM,2019:1533-1542.
[7]CHIN J Y,ZHAO K,JOTY S,et al.ANR:Aspect-based neural recommender[C]//Proceedings of CIKM.ACM,2018:147-156.
[8]ZHENG L,NOROOZI V,YU P S.Joint deep modeling of users and items using reviews for recommendation[C]//Proceedings of WSDM.ACM,2017:425-434.
[9]SEO S Y,JING H,HAO Y,et al.Interpretable convolutional neural networks with dual local and global attention for review rating prediction[C]//Proceedings of RecSys.ACM,2017:297-305.
[10]CHEN C,ZHANG M,LIU Y,et al.Neural attentional rating regression with review-level explanations[C]//Proceedings of the 2018 World Wide Web Conference.ACM,2018:1583-1592.
[11]TAY LUU A,HUI S.Multi-pointer co-attention networks for recommend-dation[C]//Proceedings of SIGKDD.ACM,2018:2309-2318.
[12]WU C,WU F,LIU J,et al.Hierarchical user and item representation with three-tier attention for recommendation[C]//Proceedings of ACL.ACL,2019:1818-1826.
[13]SAH A,DWIVEDI P.Knowledge transfer by domain-indepen-dent user latent factor for cross-domain recommender systems[J].FGCS,2020,108(7):320-333.
[14]ZHAO C,LI C,XIAO R,et al.CATN:Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network[C]//Proceedings of SIGIR.ACM,2020:229-238.
[15]KANG Y,GAI S,ZHAO F,et al.Deep Transfer Collaborative Filtering with Geometric Structure Preservation for Cross-Domain Recommendation [C]//IJCNN.IEEE,2020:1-8.
[16]LI P,TUZHILIN A.DDTCDR:Deep Dual Transfer Cross Domain Recommendation[C]//Proceedings of WSDM.ACM,2020:331-339.
[17]HONG W,ZHENG N,XIONG Z,et al.A Parallel Deep Neural Network Using Reviews and Item Metadata for Cross-Domain Recommendation[J].IEEE Access,2020,8(2):41774-41783.
[18]ZHAO C,LI C,FU C.Cross-Domain Recom mendation via Pre-ference Propagation Graph-Net[C]//Proceedings of CIKM.ACM,2019:2165-2168.
[19]YANG O,GUO B,TANG X,et al.Mobile App Cross-Domain Recommendation with Multi-Graph Neural Network[J].Trans. Knowl. Discov. Data.ACM,2021,15(4):1-21.
[20]CHAHAL D,GUPTA P.Implementation and comparison oftopic modeling techniques based on user reviews in e-commerce recommendations[J].Journal of Ambient Intelligence and Humanized Computing,2021,12(5):5055-5070.
[21]DU Y,WANG L,PENG Z,et al.review-based Hierar-chical Attention Cooperative Neural Networks for Recommendation[J].Neurocomputing,2021,447(4):38-47.
[22]LIU H,WANG W,CHEN H,et al.Hiera-rchical Multi-view Attention for Neural Review Based Recommendation[C]//NLPCC.Cham:Springer,2020:267-278.
[23]TZENG E,HOFFMAN J,SAENKO K,et al.Adversarial Discriminative Domain Adaptation[C]//Proceedings of CVPR.IEEE,2017:7167-7176.
[24]HE R,MCAULEY J.Ups and Downs:Modeling the VisualEvolution of Fashion Trends with One-Class Collaborative Filtering [C]//WWW.ACM,2016:507-517.
[25]ZHU Y,TANG Z,LIU Y,et al.Personalized Transfer of User Preferences for Cross-domain Recommendation[C]//Procee-dings of WSDM.ACM,2022:1507-1515.

相关文章 15

[1]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[2]	戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105
[3]	尹文兵, 高戈, 曾邦, 王霄, 陈怡. 基于时频域生成对抗网络的语音增强算法 Speech Enhancement Based on Time-Frequency Domain GAN 计算机科学, 2022, 49(6): 187-192. https://doi.org/10.11896/jsjkx.210500114
[4]	徐辉, 康金梦, 张加万. 基于特征感知的数字壁画复原方法 Digital Mural Inpainting Method Based on Feature Perception 计算机科学, 2022, 49(6): 217-223. https://doi.org/10.11896/jsjkx.210500105
[5]	高志宇, 王天荆, 汪悦, 沈航, 白光伟. 基于生成对抗网络的5G网络流量预测方法 Traffic Prediction Method for 5G Network Based on Generative Adversarial Network 计算机科学, 2022, 49(4): 321-328. https://doi.org/10.11896/jsjkx.210300240
[6]	黎思泉, 万永菁, 蒋翠玲. 基于生成对抗网络去影像的多基频估计算法 Multiple Fundamental Frequency Estimation Algorithm Based on Generative Adversarial Networks for Image Removal 计算机科学, 2022, 49(3): 179-184. https://doi.org/10.11896/jsjkx.201200081
[7]	李建, 郭延明, 于天元, 武与伦, 王翔汉, 老松杨. 基于生成对抗网络的多目标类别对抗样本生成算法 Multi-target Category Adversarial Example Generating Algorithm Based on GAN 计算机科学, 2022, 49(2): 83-91. https://doi.org/10.11896/jsjkx.210800130
[8]	谈馨悦, 何小海, 王正勇, 罗晓东, 卿粼波. 基于Transformer交叉注意力的文本生成图像技术 Text-to-Image Generation Technology Based on Transformer Cross Attention 计算机科学, 2022, 49(2): 107-115. https://doi.org/10.11896/jsjkx.210600085
[9]	陈贵强, 何军. 自然场景下遥感图像超分辨率重建算法研究 Study on Super-resolution Reconstruction Algorithm of Remote Sensing Images in Natural Scene 计算机科学, 2022, 49(2): 116-122. https://doi.org/10.11896/jsjkx.210700095
[10]	石达, 芦天亮, 杜彦辉, 张建岭, 暴雨轩. 基于改进CycleGAN的人脸性别伪造图像生成模型 Generation Model of Gender-forged Face Image Based on Improved CycleGAN 计算机科学, 2022, 49(2): 31-39. https://doi.org/10.11896/jsjkx.210600012
[11]	唐雨潇, 王斌君. 基于深度生成模型的人脸编辑研究进展 Research Progress of Face Editing Based on Deep Generative Model 计算机科学, 2022, 49(2): 51-61. https://doi.org/10.11896/jsjkx.210400108
[12]	张玮琪, 汤轶丰, 李林燕, 胡伏原. 基于场景图的段落生成序列图像方法 Image Stream From Paragraph Method Based on Scene Graph 计算机科学, 2022, 49(1): 233-240. https://doi.org/10.11896/jsjkx.201100207
[13]	蒋宗礼, 樊珂, 张津丽. 基于生成对抗网络和元路径的异质网络表示学习 Generative Adversarial Network and Meta-path Based Heterogeneous Network Representation Learning 计算机科学, 2022, 49(1): 133-139. https://doi.org/10.11896/jsjkx.201000179
[14]	徐涛, 田崇阳, 刘才华. 基于深度学习的人群异常行为检测综述 Deep Learning for Abnormal Crowd Behavior Detection:A Review 计算机科学, 2021, 48(9): 125-134. https://doi.org/10.11896/jsjkx.201100015
[15]	林椹尠, 张梦凯, 吴成茂, 郑兴宁. 利用生成对抗网络的人脸图像分步补全法 Face Image Inpainting with Generative Adversarial Network 计算机科学, 2021, 48(9): 174-180. https://doi.org/10.11896/jsjkx.200800014

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed