Proceedings

A^3NCF: An Adaptive Aspect Attention Model for Rating Prediction

Download BibTeX Cite

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. Main track. Pages 3748-3754.

https://doi.org/10.24963/ijcai.2018/521

© 2018 International Joint Conferences on Artificial Intelligence

Abstract

Current recommender systems consider the various aspects of items for making accurate recommendations. Different users place different importance to these aspects which can be thought of as a preference/attention weight vector. Most existing recommender systems assume that for an individual, this vector is the same for all items. However, this assumption is often invalid, especially when considering a user's interactions with items of diverse characteristics. To tackle this problem, in this paper, we develop a novel aspect-aware recommender model named A$^3$NCF, which can capture the varying aspect attentions that a user pays to different items. Specifically, we design a new topic model to extract user preferences and item characteristics from review texts. They are then used to 1) guide the representation learning of users and items, and 2) capture a user's special attention on each aspect of the targeted item with an attention network. Through extensive experiments on several large-scale datasets, we demonstrate that our model outperforms the state-of-the-art review-aware recommender systems in the rating prediction task.

  1. [Bao et al., 2014] Yang Bao, Hui Fang, and Jie Zhang. Topicmf: Simultaneously exploiting ratings and reviews for recommenda- tion. In AAAI, volume 14, pages 2-8, 2014.
  2. [Bell and Koren, 2007] Robert M Bell and Yehuda Koren. Lessons from the netflix prize challenge. ACM SIGKDD Explorations Newsletter, 9(2):75-79, 2007.
  3. [Blei et al., 2003] David M Blei, Andrew Y Ng, and Michael I Jor- dan. Latent dirichlet allocation. Journal of Machine Learning Research, 3(Jan):993-1022, 2003.
  4. [Cao et al., 2018] Da Cao, Xiangnan He, Lianhai Miao, Yahui An, Chao Yang, and Richang Hong. Attentive group recommenda- tion. In ACM SIGIR, 2018.
  5. [Catherine and Cohen, 2017] Rose Catherine and William Cohen. Transnets: Learning to transform for recommendation. In ACM RecSys, pages 288-296, 2017.
  6. [Cheng and Shen, 2016] Zhiyong Cheng and Jialie Shen. On effec- tive location-aware music recommendation. ACM Transactions on Information Systems (TOIS), 34(2):13, 2016.
  7. [Cheng et al., 2016] Zhiyong Cheng, Shen Jialie, and Steven CH Hoi. On effective personalized music retrieval by exploring on- line user behaviors. In ACM SIGIR, pages 125-134, 2016.
  8. [Cheng et al., 2018] Zhiyong Cheng, Ying Ding, Lei Zhu, and Kankanhalli Mohan. Aspect-aware latent factor model: Rating prediction with ratings and reviews. In WWW, pages 639-648, 2018.
  9. [Covington et al., 2016] Paul Covington, Jay Adams, and Emre Sargin. Deep neural networks for youtube recommendations. In ACM RecSys, pages 191-198, 2016.
  10. [He et al., 2015] Xiangnan He, Tao Chen, Min-Yen Kan, and Xiao Chen. Trirank: Review-aware explainable recommendation by modeling aspects. In ACM CIKM, pages 1661-1670, 2015.
  11. [He et al., 2017] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collaborative filtering. In WWW, pages 173-182, 2017.
  12. [Hong et al., 2016a] Richang Hong, Zhenzhen Hu, Ruxin Wang, Meng Wang, and Dacheng Tao. Multi-view object retrieval via multi-scale topic models. IEEE Trans. Image Process., 25(12):5814-5827, 2016.
  13. [Hong et al., 2016b] Richang Hong, Luming Zhang, Chao Zhang, and Roger Zimmermann. Flickr circles: aesthetic tendency dis- covery by multi-view regularized topic modeling. IEEE Trans. Multimed., 18(8):1555-1567, 2016.
  14. [Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  15. [Koren et al., 2009] Yehuda Koren, Robert Bell, and Chris Volin- sky. Matrix factorization techniques for recommender systems. Computer, 42(8):42-49, 2009.
  16. [Ling et al., 2014] Guang Ling, Michael R Lyu, and Irwin King. Ratings meet reviews, a combined approach to recommend. In ACM RecSys, pages 105-112, 2014.
  17. [Maas et al., 2013] Andrew L Maas, Awni Y Hannun, and An- drew Y Ng. Rectifier nonlinearities improve neural network acoustic models. In Proc. ICML, 2013.
  18. [McAuley and Leskovec, 2013] Julian McAuley and Jure Leskovec. Hidden factors and hidden topics: understand- ing rating dimensions with review text. In ACM RecSys, pages 165-172, 2013.
  19. [Nie et al., 2015] Liqiang Nie, Meng Wang, Luming Zhang, Shuicheng Yan, Bo Zhang, and Tat-Seng Chua. Disease inference from health-related questions via sparse deep learning. IEEE Trans. Knowledge Data Eng., 27(8):2107-2119, 2015.
  20. [Qiu et al., 2016] Lin Qiu, Sheng Gao, Wenlong Cheng, and Jun Guo. Aspect-based latent factor model by integrating ratings and reviews for recommender system. Knowledge-Based Systems, 110:233-243, 2016.
  21. [Song et al., 2018] Xuemeng Song, Fuli Feng, Xianjing Han, Xin Yang, Wei Liu, and Liqiang Nie. Neural compatibility modeling with attentive knowledge distillation. In ACM SIGIR, 2018.
  22. [Srivastava et al., 2014] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, 15(1):1929-1958, 2014.
  23. [Tan et al., 2016] Yunzhi Tan, Min Zhang, Yiqun Liu, and Shaop- ing Ma. Rating-boosted latent topics: Understanding users and items with ratings and reviews. In IJCAI, 2016. IJCAI
  24. [Tang et al., 2015] Duyu Tang, Bing Qin, Ting Liu, and Yuekui Yang. User modeling with neural network for review rating pre- diction. In IJCAI, pages 1340-1346, 2015. IJCAI
  25. [Wang and Blei, 2011] Chong Wang and David M Blei. Collabora- tive topic modeling for recommending scientific articles. In ACM KDD, pages 448-456, 2011.
  26. [Wang et al., 2018] Xiang Wang, Xiangnan He, Fuli Feng, Liqiang Nie, and Tat-Seng Chua. TEM: Tree-enhanced embedding model for explainable recommendation. In WWW, pages 1543-1552, 2018.
  27. [Zhang and Wang, 2016] Wei Zhang and Jianyong Wang. Integrat- ing topic and latent factors for scalable personalized review- based rating prediction. IEEE Transactions on Knowledge and Data Engineering, 28(11):3013-3027, 2016.
  28. [Zhang et al., 2014] Yongfeng Zhang, Guokun Lai, Min Zhang, Yi Zhang, Yiqun Liu, and Shaoping Ma. Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In ACM SIGIR, pages 83-92, 2014.
  29. [Zhang et al., 2016] Wei Zhang, Quan Yuan, Jiawei Han, and Jiany- ong Wang. Collaborative multi-level embedding learning from reviews for rating prediction. In IJCAI, pages 2986-2992, 2016. IJCAI
  30. [Zhang et al., 2017] Yongfeng Zhang, Qingyao Ai, Xu Chen, and W. Bruce Croft. Joint representation learning for top-n recom- mendation with heterogeneous information sources. In ACM CIKM, pages 1449-1458, 2017.
  31. [Zheng et al., 2017] Lei Zheng, Vahid Noroozi, and Philip S Yu. Joint deep modeling of users and items using reviews for recom- mendation. In ACM WSDM, pages 425-434, 2017.

References were extracted automatically from the PDF and may contain errors.

Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards