TY - GEN
T1 - DMRAN
T2 - 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
AU - Wang, Huizhao
AU - Liu, Guanfeng
AU - Liu, An
AU - Li, Zhixu
AU - Zheng, Kai
PY - 2019
Y1 - 2019
N2 - The conventional methods for the next-item recommendation are generally based on RNN or one-dimensional attention with time encoding. They are either hard to preserve the long-term dependencies between different interactions, or hard to capture fine-grained user preferences. In this paper, we propose a Double Most Relevant Attention Network (DMRAN) that contains two layers, i.e., Item level Attention and Feature Level Self-attention, which are to pick out the most relevant items from the sequence of user's historical behaviors, and extract the most relevant aspects of relevant items, respectively. Then, we can capture the fine-grained user preferences to better support the next-item recommendation. Extensive experiments on two real-world datasets illustrate that DMRAN can improve the efficiency and effectiveness of the recommendation compared with the state-of-the-art methods.
AB - The conventional methods for the next-item recommendation are generally based on RNN or one-dimensional attention with time encoding. They are either hard to preserve the long-term dependencies between different interactions, or hard to capture fine-grained user preferences. In this paper, we propose a Double Most Relevant Attention Network (DMRAN) that contains two layers, i.e., Item level Attention and Feature Level Self-attention, which are to pick out the most relevant items from the sequence of user's historical behaviors, and extract the most relevant aspects of relevant items, respectively. Then, we can capture the fine-grained user preferences to better support the next-item recommendation. Extensive experiments on two real-world datasets illustrate that DMRAN can improve the efficiency and effectiveness of the recommendation compared with the state-of-the-art methods.
UR - http://www.scopus.com/inward/record.url?scp=85074911111&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2019/513
DO - 10.24963/ijcai.2019/513
M3 - Conference proceeding contribution
AN - SCOPUS:85074911111
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 3698
EP - 3704
BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
A2 - Kraus, Sarit
PB - International Joint Conferences on Artificial Intelligence
CY - Freiburg, Germany
Y2 - 10 August 2019 through 16 August 2019
ER -