ABSTRACT
Predicting users' actions based on anonymous sessions is a challenging problem in web-based behavioral modeling research, mainly due to the uncertainty of user behavior and the limited information. Recent advances in recurrent neural networks have led to promising approaches to solving this problem, with long short-term memory model proving effective in capturing users' general interests from previous clicks. However, none of the existing approaches explicitly take the effects of users' current actions on their next moves into account. In this study, we argue that a long-term memory model may be insufficient for modeling long sessions that usually contain user interests drift caused by unintended clicks. A novel short-term attention/memory priority model is proposed as a remedy, which is capable of capturing users' general interests from the long-term memory of a session context, whilst taking into account users' current interests from the short-term memory of the last-clicks. The validity and efficacy of the proposed attention mechanism is extensively evaluated on three benchmark data sets from the RecSys Challenge 2015 and CIKM Cup 2016. The numerical results show that our model achieves state-of-the-art performance in all the tests.
Supplemental Material
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of ICLR'15. CoRR, Scottsdale, USA.Google Scholar
- Hidasi Balázs, Massimo Quadrana, Alexandros Karatzoglou, and Domonkos Tikk. 2016. Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations. In Proceedings of ACM RecSys'16. ACM, Boston, Massachusetts, USA, 241--248. Google ScholarDigital Library
- Wanrong Gu, Shoubin Dong, and Zhizhao Zeng. 2014. Increasing recommended effectiveness with markov chains and purchase intervals. Neural Computing and Applications 25, 5 (2014), 1153--1162. Google ScholarDigital Library
- Xiangnan He, Hanwang Zhang, Min-Yen Kan, and Tat-Seng Chua. 2016. Fast matrix factorization for online recommendation with implicit feedback. In Proceedings of ACM SIGIR'16. ACM, Pisa, Italy, 549--558. Google ScholarDigital Library
- Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. In Proceedings of ICLR'15 (May 2 - 4). CoRR, San Juan, Puerto Rico.Google Scholar
- Liang Hu, Longbing Cao, Shoujin Wang, Guandong Xu, Jian Cao, and Zhiping Gu. 2017. Diversifying Personalized Recommendation with User-session Context. In Proceedings of IJCAI'17. IJCAI, Melbourne, Australia, 1858 -- 1864. Google ScholarDigital Library
- Dietmar Jannach, Lukas Lerche, and Michael Jugovac. 2015. Adaptation and Evaluation of Recommendations for Short-term Shopping Goals. In Proceedings of ACM RecSys'15 (September 16 - 20). ACM, Vienna, Austria, 211--218. Google ScholarDigital Library
- Yehuda Koren, Robert Bell, and Chris Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer 42, 8 (2009). Google ScholarDigital Library
- Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. Nature 521, 7553 (2015), 436--444.Google Scholar
- Jing Li, Pengjie Ren, Zhumin Chen, Zhaochun Ren, and Jun Ma. 2017. Neural Attentive Session-based Recommendation. In Proceedings of ACM CIKM'17. Singapore, Singapore, 1419--1428. Google ScholarDigital Library
- Minh-Thang Luong, Hieu Pham, and Christopher D.Manning. 2015. Effective Approaches to Attention-based Neural Machine Translation. In Proceedings of EMNLP'15 (September 17 - 21). Association for Computational Linguistics, Lisbon, Portugal, 1412--1421.Google Scholar
- Massimo Quadrana, Alexandros Karatzoglou, Hidasi Balázs, and Paolo Cremonesi. 2017. Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks. In Proceedings of ACM RecSys'17. ACM, Como, Italy, 130--137. Google ScholarDigital Library
- Steffen Rendle, Christoph Freudenthaler, and Lars Schmidt-Thieme. 2010. Factorizing personalized Markov chains for next-basket recommendation. In Proceedings of WWW'10. ACM, Raleigh, North Carolina, USA, 811--820. Google ScholarDigital Library
- Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. 2001. Item-based collaborative filtering recommendation algorithms. In Proceedings of WWW'01. ACM, 285--295. Google ScholarDigital Library
- Guy Shani, David Heckerman, and Ronen I Brafman. 2005. An MDP-based recommender system. JMLR 6, Sep (2005), 1265--1295. Google ScholarDigital Library
- Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. In Proceedings of NIPS'14 (December 08 - 13). MIT Press, Montreal, Canada, 3104--3112. Google ScholarDigital Library
- Yong Kiam Tan, Xinxing Xu, and Yong Liu. 2016. Improved Recurrent Neural Networks for Session-based Recommendations. In Proceedings of DLRS'16 (September 15 - 15). ACM, Boston, MA, USA, 17--22. Google ScholarDigital Library
- Bartlomiej Twardowski. 2016. Modelling Contextual Information in Session- Aware Recommender Systems with Neural Networks. In Proceedings of ACM RecSys'16 (September 15 - 19). ACM, Boston, MA, USA, 273--276. Google ScholarDigital Library
- Pengfei Wang, Jiafeng Guo, Yanyan Lan, Jun Xu, Shengxian Wan, and Xueqi Cheng. 2015. Learning Hierarchical Representation Model for NextBasket Recommendation. In Proceedings of ACM SIGIR'15. ACM, Santiago, Chile, 403--412. Google ScholarDigital Library
- Feng Yu, Qiang Liu, Shu Wu, Liang Wang, and Tieniu Tan. 2016. A Dynamic Recurrent Model for Next Basket Recommendation. In Proceedings of ACM SIGIR'16 (July 17 - 21). ACM, Pisa, Italy, 729--732. Google ScholarDigital Library
- Yu Zhu, Hao Li, Yikang Liao, BeidouWang, Ziyu Guan, Haifeng Liu, and Deng Cai. 2017. What to Do Next: Modeling User Behaviors by Time-LSTM. In Proceedings of IJCAI'17 (August 19 - 25). IJCAI, Melbourne, Australia, 3602--360. Google ScholarDigital Library
Index Terms
- STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation
Recommendations
A Dynamic Co-attention Network for Session-based Recommendation
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementSession-based recommendation is the task of recommending the next item a user might be interested in given partially known session information, e.g., part of a session or recent historical sessions. An effective session-based recommender should be able ...
Modeling Long-Term and Short-Term Interests with Parallel Attentions for Session-Based Recommendation
Database Systems for Advanced ApplicationsAbstractThe aim of session-based recommendation is to predict the users’ next clicked item, which is a challenging task due to the inherent uncertainty in user behaviors and anonymous implicit feedback information. A powerful session-based recommender can ...
Dynamic global structure enhanced multi-channel graph neural network for session-based recommendation
AbstractSession-based recommendation is a challenging task, which aims at making recommendation for anonymous users based on in-session data, i.e. short-term interaction data. Most session-based recommendation methods only model user’s ...
Comments