Standard

Interacting Attention-gated Recurrent Networks for Recommendation. / Pei, Wenjie; Yang, Jie; Sun, Zhu; Zhang, Jie; Bozzon, Alessandro; Tax, David.

CIKM'17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York : Association for Computing Machinery (ACM), 2017. p. 1459-1468 .

Research output: Scientific - peer-reviewConference contribution

Harvard

Pei, W, Yang, J, Sun, Z, Zhang, J, Bozzon, A & Tax, D 2017, Interacting Attention-gated Recurrent Networks for Recommendation. in CIKM'17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management. Association for Computing Machinery (ACM), New York, pp. 1459-1468 , The 2017 ACM on Conference on Information and Knowledge Management, Singapore, Singapore, 6-10 November. DOI: 10.1145/3132847.3133005

APA

Pei, W., Yang, J., Sun, Z., Zhang, J., Bozzon, A., & Tax, D. (2017). Interacting Attention-gated Recurrent Networks for Recommendation. In CIKM'17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management. (pp. 1459-1468 ). New York: Association for Computing Machinery (ACM). DOI: 10.1145/3132847.3133005

Vancouver

Pei W, Yang J, Sun Z, Zhang J, Bozzon A, Tax D. Interacting Attention-gated Recurrent Networks for Recommendation. In CIKM'17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York: Association for Computing Machinery (ACM). 2017. p. 1459-1468 . Available from, DOI: 10.1145/3132847.3133005

Author

Pei, Wenjie; Yang, Jie; Sun, Zhu; Zhang, Jie; Bozzon, Alessandro; Tax, David / Interacting Attention-gated Recurrent Networks for Recommendation.

CIKM'17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York : Association for Computing Machinery (ACM), 2017. p. 1459-1468 .

Research output: Scientific - peer-reviewConference contribution

BibTeX

@inbook{b17ebcef1e1c4ef08b4f979d8e7faa32,
title = "Interacting Attention-gated Recurrent Networks for Recommendation",
keywords = "Recurrent Neural Network, Attention Model, User-item Interaction, Feature-based Recommendation",
author = "Wenjie Pei and Jie Yang and Zhu Sun and Jie Zhang and Alessandro Bozzon and David Tax",
year = "2017",
month = "11",
doi = "10.1145/3132847.3133005",
pages = "1459--1468",
booktitle = "CIKM'17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

RIS

TY - CHAP

T1 - Interacting Attention-gated Recurrent Networks for Recommendation

AU - Pei,Wenjie

AU - Yang,Jie

AU - Sun,Zhu

AU - Zhang,Jie

AU - Bozzon,Alessandro

AU - Tax,David

PY - 2017/11

Y1 - 2017/11

N2 - Capturing the temporal dynamics of user preferences over items is important for recommendation. Existing methods mainly assume that all time steps in user-item interaction history are equally relevant to recommendation, which however does not apply in real-world scenarios where user-item interactions can often happen accidentally. More importantly, they learn user and item dynamics separately, thus failing to capture their joint effects on user-item interactions. To better model user and item dynamics, we present the Interacting Attention-gated Recurrent Network (IARN) which adopts the attention model to measure the relevance of each time step. In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions. By doing so, IARN can selectively memorize different time steps of a user's history when predicting her preferences over different items. Our model can therefore provide meaningful interpretations for recommendation results, which could be further enhanced by auxiliary features. Extensive validation on real-world datasets shows that IARN consistently outperforms state-of-the-art methods.

AB - Capturing the temporal dynamics of user preferences over items is important for recommendation. Existing methods mainly assume that all time steps in user-item interaction history are equally relevant to recommendation, which however does not apply in real-world scenarios where user-item interactions can often happen accidentally. More importantly, they learn user and item dynamics separately, thus failing to capture their joint effects on user-item interactions. To better model user and item dynamics, we present the Interacting Attention-gated Recurrent Network (IARN) which adopts the attention model to measure the relevance of each time step. In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions. By doing so, IARN can selectively memorize different time steps of a user's history when predicting her preferences over different items. Our model can therefore provide meaningful interpretations for recommendation results, which could be further enhanced by auxiliary features. Extensive validation on real-world datasets shows that IARN consistently outperforms state-of-the-art methods.

KW - Recurrent Neural Network

KW - Attention Model

KW - User-item Interaction

KW - Feature-based Recommendation

U2 - 10.1145/3132847.3133005

DO - 10.1145/3132847.3133005

M3 - Conference contribution

SP - 1459

EP - 1468

BT - CIKM'17 Proceedings of the 2017 ACM Conference on Information and Knowledge Management

PB - Association for Computing Machinery (ACM)

ER -

ID: 33899749