ABSTRACT
Two-tower neural networks are popularly used in review-aware recommender systems, in which two encoders are separately employed to learn representations for users and items from reviews. However, such an architecture isolates the information exchange between two encoders, resulting in suboptimal recommendation accuracy. To this end, we propose a novel two-tower style Neural Recommendation with Cross-modality Mutual Attention (NRCMA), which bridges user encoder and item encoder crossing reviews and ratings, in order to select informative words and reviews to learn better representation for users and items. Extensive experiments on three benchmark datasets demonstrate that the cross-modality mutual attention is beneficial to two-tower neural networks, and NRCMA consistently outperforms state-of-the-art review-aware item recommendation techniques.
Supplemental Material
- D. M. Blei, A. Y. Ng, and M. I. Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research, Vol. 3, Jan (2003), 993--1022. Google ScholarDigital Library
- Fidel Cacheda, Victor Carneiro, Diego Ferná ndez, and Vreixo Formoso. 2011. Comparison of collaborative filtering algorithms: Limitations of current techniques and proposals for scalable, high-performance recommender systems. ACM Trans. Web, Vol. 5, 1 (2011), 2:1--2:33. Google ScholarDigital Library
- Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural Collaborative Filtering. In WWW. ACM, 173--182.Google Scholar
- Yehuda Koren, Robert M. Bell, and Chris Volinsky. 2009. Matrix Factorization Techniques for Recommender Systems. Computer, Vol. 42, 8 (2009), 30--37. Google ScholarDigital Library
- Donghua Liu, Jing Li, Bo Du, Jun Chang, and Rong Gao. 2019 a. DAML: Dual Attention Mutual Learning between Ratings and Reviews for Item Recommendation. In SIGKDD. ACM, 344--352. Google ScholarDigital Library
- Hongtao Liu, Fangzhao Wu, Wenjun Wang, Xianchen Wang, Pengfei Jiao, Chuhan Wu, and Xing Xie. 2019 b. NRPA: Neural Recommendation with Personalized Attention. In SIGIR. ACM, 1233--1236. Google ScholarDigital Library
- Julian J. McAuley and Jure Leskovec. 2013. Hidden factors and hidden topics: understanding rating dimensions with review text. In RecSys. ACM, 165--172. Google ScholarDigital Library
- Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global Vectors for Word Representation. In EMNLP. ACL, 1532--1543.Google Scholar
- Steffen Rendle. 2010. Factorization Machines. In ICDM. IEEE, 995--1000. Google ScholarDigital Library
- Noveen Sachdeva and Julian J. McAuley. 2020. How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements. In SIGIR. ACM, 1845--1848. Google ScholarDigital Library
- Sungyong Seo, Jing Huang, Hao Yang, and Yan Liu. 2017. Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction. In RecSys. ACM, 297--305. Google ScholarDigital Library
- Lei Zheng, Vahid Noroozi, and Philip S. Yu. 2017. Joint Deep Modeling of Users and Items Using Reviews for Recommendation. In WSDM. ACM, 425--434. Google ScholarDigital Library
Index Terms
- Review-Aware Neural Recommendation with Cross-Modality Mutual Attention
Recommendations
DAML: Dual Attention Mutual Learning between Ratings and Reviews for Item Recommendation
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningDespite the great success of many matrix factorization based collaborative filtering approaches, there is still much space for improvement in recommender system field. One main obstacle is the cold-start and data sparseness problem, requiring better ...
Attentive Aspect Modeling for Review-Aware Recommendation
In recent years, many studies extract aspects from user reviews and integrate them with ratings for improving the recommendation performance. The common aspects mentioned in a user’s reviews and a product’s reviews indicate indirect connections between ...
Attention-Based Neural Tag Recommendation
Database Systems for Advanced ApplicationsAbstractPersonalized tag recommender systems suggest tags to users when annotating specific items. Usually, recommender systems need to take both users’ preference and items’ features into account. Existing methods like latent factor models based on ...
Comments