Cross Domain Rating Prediction Based on Aspect and Capsule Network

LIANG Shun-pan; LIU Wei; ZHENG Zhi-zhong; YUAN Fu-yong

doi:10.12263/DZXB.20210483

您当前的位置：

首页 >

文章列表页 >

Cross Domain Rating Prediction Based on Aspect and Capsule Network

PAPERS | 更新时间：2025-12-08

- Cross Domain Rating Prediction Based on Aspect and Capsule Network
- ACTA ELECTRONICA SINICA Vol. 50, Issue 9, Pages: 2102-2109(2022)
- 作者机构：
  
  燕山大学信息科学与工程学院, 河北秦皇岛 066004
- 作者简介：
- 基金信息：
- DOI：10.12263/DZXB.20210483
  CLC： TP391
- Received：15 April 2021，
  
  Revised：2021-11-08，
  
  Published：25 September 2022
- 稿件说明：
移动端阅览
梁顺攀,刘伟,郑智中等.基于方面和胶囊网络的跨域评分预测模型[J].电子学报,2022,50(09):2102-2109.

LIANG Shun-pan,LIU Wei,ZHENG Zhi-zhong,et al.Cross Domain Rating Prediction Based on Aspect and Capsule Network[J].ACTA ELECTRONICA SINICA,2022,50(09):2102-2109.
梁顺攀,刘伟,郑智中等.基于方面和胶囊网络的跨域评分预测模型[J].电子学报,2022,50(09):2102-2109. DOI： 10.12263/DZXB.20210483.

LIANG Shun-pan,LIU Wei,ZHENG Zhi-zhong,et al.Cross Domain Rating Prediction Based on Aspect and Capsule Network[J].ACTA ELECTRONICA SINICA,2022,50(09):2102-2109. DOI： 10.12263/DZXB.20210483.

摘要

用户评论可以反映用户对项目的偏好信息，将用户在其他领域的偏好迁移到目标领域进行跨域推荐，可以缓解目标域数据稀疏引起的冷启动问题.本文针对传统的跨域推荐方法无法将完整的用户偏好进行迁移以及传统的方面提取方法预测精度不高两个问题，提出基于方面和胶囊网络的跨域评分预测模型ACN（Aspect and Capsule Network）.ACN模型使用胶囊网络挖掘评论文档的多个方面，然后通过注意力机制筛选出对目标域最重要的特征，迁移到目标域进行评分预测.最后，通过实验证明ACN模型分别在单一源域和多源域的情况下，较基准模型最高有2.3%和20.8%的性能提升.

Abstract

Users'reviews on items can reflect users'preference information. Migrating users'preferences in other fields to the target domain for cross domain recommendation can alleviate the cold start problem caused by sparse data in the target domain. Aiming at the two problems that the traditional cross domain recommendation methods can not migrate the complete user preferences and the prediction accuracy of the traditional aspect extraction methods is incorrect

this paper proposes a cross domain score prediction model based on aspect and capsule network(ACN). ACN uses capsule network to mine multiple aspects of review documents

and then selects the most important features for the target domain through attention mechanism

and migrate to the target domain for score prediction. Compared with the benchmark model

ACN has the highest performance improvement of 2.3% and 20.8% when using single source domain and multi-source domain.

关键词

Keywords

references

LUO X , ZHOU M C , LI S , et al . Algorithms of unconstrained non-negative latent factor analysis for recommender systems [J]. IEEE Transactions on Big Data , 2021 , 7 ( 1 ): 227 - 240 .

LUO X , WANG D X , ZHOU M C , et al . Latent factor-based recommenders relying on extended stochastic gradient descent algorithms [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2021 , 51 ( 2 ): 916 - 926 .

WU D , LUO X , SHANG M S , et al . A deep latent factor model for high-dimensional and sparse matrices in recommender systems [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems , 2021 , 51 ( 7 ): 4285 - 4296 .

李林峰 , 刘真 , 魏港明 , 等 . 基于共享知识模型的跨领域推荐算法 [J]. 电子学报 , 2018 , 46 ( 8 ): 1947 - 1953 .

LI L F , LIU Z , WEI G M , et al . Cross-domain recommendation algorithm based on sharing knowledge pattern [J]. Acta Electronica Sinica , 2018 , 46 ( 8 ): 1947 - 1953 . (in Chinese)

SINGH A P , GORDON G J . Relational learning via collective matrix factorization [C]// Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM , 2008 : 650 - 658 .

MAN T , SHEN H W , JIN X L , et al . Cross-domain recommendation: an embedding and mapping approach [C]// Proceedings of the 26th International Joint Conference on Artificial Intelligence . Palo Alto : AAAI Press , 2017 : 2464 - 2470 .

ZHU Feng , WANG Yan , CHEN Chaochao , et al . A deep framework for cross-domain and cross-system recommendations [C]// Proceedings of the 27th International Joint Conference on Artificial Intelligence . Stockholm, Sweden : AAAI Press , 2018 : 3711 - 3717 .

刘真 , 田靖玉 , 苑宝鑫 , 等 . 基于知识聚合和迁移的跨领域推荐算法 [J]. 电子学报 , 2020 , 48 ( 10 ): 1928 - 1932 .

LIU Z , TIAN J Y , YUAN B X , et al . Cross-domain recommendation algorithm based on knowledge aggregation and transfer [J]. Acta Electronica Sinica , 2020 , 48 ( 10 ): 1928 - 1932 . (in Chinese)

ELKAHKY A M , SONG Y , HE X D . A multi-view deep learning approach for cross domain user modeling in recommendation systems [C]// WWW'15: Proceedings of the 24th International Conference on World Wide Web. New York: ACM , 2015 : 278 - 288 .

SONG T H , PENG Z H , WANG S Z , et al . Review-based cross-domain recommendation through joint tensor factorization [C]// International Conference on Database Systems for Advanced Applications . Cham : Springer , 2017 : 525 - 540 .

FU W J , PENG Z H , WANG S Z , et al . Deeply fusing reviews and contents for cold start users in cross-domain recommendation systems [C]// The Thirty-Third AAAI Conference on Artificial Intelligence . Palo Alto : AAAI , 2019 : 94 - 101 .

ZHAO C , LI C L , XIAO R , et al . CATN: cross-domain recommendation for cold-start users via aspect transfer network [C]// SIGIR'20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2020 : 229 - 238 .

CHENG Z Y , DING Y , ZHU L , et al . Aspect-aware latent factor model: Rating prediction with ratings and reviews [C]// WWW'18: Proceedings of the 2018 World Wide Web Conference. New York: ACM , 2018 : 639 - 648 .

BAHDANAU D , CHO K , BENGIO Y . Neural machine translation by jointly learning to align and translate [EB/OL]. ( 2014-09-01 ). https://arxiv.org/abs/1409.0473 https://arxiv.org/abs/1409.0473 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems . Red Hook, NY : Curran Associates Inc , 2017 : 6000 - 6010 .

Sabour S , Frosst N , Hinton G E . Dynamic routing between capsules [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems . Red Hook, NY : Curran Associates Inc , 2017 : 3859 - 3869 .

郑启航 , 王章权 , 刘半藤 , 等 . 基于加性间距胶囊网络的家庭活动识别方法研究 [J]. 电子学报 , 2020 , 48 ( 8 ): 1580 - 1586 .

ZHENG Q H , WANG Z Q , LIU B T , et al . Research on family activity recognition method based on additive margin capsule network [J]. Acta Electronica Sinica , 2020 , 48 ( 8 ): 1580 - 1586 . (in Chinese)

任开旭 , 王玉龙 , 刘同存 , 等 . 融合多维语义表示的概率矩阵分解模型 [J]. 电子学报 , 2019 , 47 ( 9 ): 1848 - 1854 .

REN K X , WANG Y L , LIU T C , et al . A probabilistic matrix factorization model based on multidimensional semantic representation learning [J]. Acta Electronica Sinica , 2019 , 47 ( 9 ): 1848 - 1854 . (in Chinese)

KINGMA D P , BA J . ADAM: A method for stochastic optimization [EB/OL].( 2014-12-22 ). https://arxiv.org/abs/1412. 6980 https://arxiv.org/abs/1412.6980 .

MCAULEY J , TARGETT C , SHI Q F , et al . Image-based recommendations on styles and substitutes [C]// Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2015 : 43 - 52 .

CHIN J Y , ZHAO K Q , JOTY S R , et al . ANR: aspect-based neural recommender [C]. Proceedings of the 27th ACM International Conference on Information and Knowledge Management . New York : ACM , 2018 . 147 - 156

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Visual Grounding Method with Contrastive Learning Large Model

Dual Attention-Guided Detail and Structure Information Fusion Network for Image Dehazing

Intrusion Detection Method Based on Capsule Network for Industrial Internet

An Attention Network with Continuous Wavelet Convolution and Graph Embedding

Related Author

Shun-pan LIANG

Wei LIU

Zhi-zhong ZHENG

Fu-yong YUAN

XUE Mo-gen

QIN Xiao-yan

ZHU Hong

YUAN Guang-lin

Related Institution

College of Information Science and Engineering， Yanshan University

Anhui Province Key Laboratory of Polarization Imaging Detection Technology

Department of Information Engineering, PLA Army Academy of Artillery and Air Defense

Graduate brigade, PLA Army Academy of Artillery and Air Defense

Yunnan Key Laboratory of Artificial Intelligence

⁰