Enhanced Attention Framework for Multi-Interest Sequential Recommendation

被引:2
作者
Yin, Dapeng [1 ]
Feng, Shuang [1 ,2 ]
机构
[1] Commun Univ China, Key Lab Convergent Media & Intelligent Technol, Minist Educ, Beijing, Peoples R China
[2] Commun Univ China, State Key Lab Media Convergence & Commun, Beijing 100024, Peoples R China
关键词
Behavioral sciences; Computational modeling; Correlation; Task analysis; Transformers; Recurrent neural networks; Matrix decomposition; Multi-interest recommendation; attention; sequential recommendation;
D O I
10.1109/ACCESS.2022.3185063
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Sequential recommendation tasks predict items to be interacted at the next moment according to users' historical behavior sequences. A large number of studies have shown that accuracy is not the only evaluation metric in the sequential recommendation tasks. Diversity can measure homogeneity of items to capture the changes of users' interests in the sequences. Integrating multiple interests of users has become the focus of current research. The existing multi-interest sequential recommendation methods adopt the method of self-attention, but it is based on the self-attention of transformer, which lacks the consideration of the correlation between different samples. Therefore, we propose an Enhanced Attention (EA) framework, which is based on two linear layers and two norm layers. Compared with self-attention, it not only reduces the high computational complexity, but also obtains the correlation between different samples. Multi-head mechanism is also applied to EA framework. We conduct experiments for the sequential recommendation on three real-world datasets, Amazon, Taobao and MovieLens-1M. The experimental results show that the EA framework is significantly improved compared with the current state-of-the-art models.
引用
收藏
页码:67703 / 67712
页数:10
相关论文
共 40 条
  • [1] Badrul S., 2001, P 10 INT C WORLD WID, P285, DOI DOI 10.1145/371920.372071
  • [2] Bell Robert M, 2007, KDD CUP WORKSHOP 13, P7, DOI DOI 10.1007/S007790170019
  • [3] Bradley K., 2001, P 12 IR C ART INT CO, V85, P141
  • [4] Controllable Multi-Interest Framework for Recommendation
    Cen, Yukuo
    Zhang, Jianwei
    Zou, Xu
    Zhou, Chang
    Yang, Hongxia
    Tang, Jie
    [J]. KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 2942 - 2951
  • [5] Sequential Recommendation with User Memory Networks
    Chen, Xu
    Xu, Hongteng
    Zhang, Yongfeng
    Tang, Jiaxi
    Cao, Yixin
    Qin, Zheng
    Zha, Hongyuan
    [J]. WSDM'18: PROCEEDINGS OF THE ELEVENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2018, : 108 - 116
  • [6] Cho K., 2014, P C EMP METH NAT LAN, P1724
  • [7] Deep Neural Networks for YouTube Recommendations
    Covington, Paul
    Adams, Jay
    Sargin, Emre
    [J]. PROCEEDINGS OF THE 10TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'16), 2016, : 191 - 198
  • [8] Guo M.-H., 2021, ARXIV210502358, V2021
  • [9] PCT: Point cloud transformer
    Guo, Meng-Hao
    Cai, Jun-Xiong
    Liu, Zheng-Ning
    Mu, Tai-Jiang
    Martin, Ralph R.
    Hu, Shi-Min
    [J]. COMPUTATIONAL VISUAL MEDIA, 2021, 7 (02) : 187 - 199
  • [10] The MovieLens Datasets: History and Context
    Harper, F. Maxwell
    Konstan, Joseph A.
    [J]. ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS, 2016, 5 (04)