Deep Bi-LSTM Networks for Sequential Recommendation

被引:17
|
作者
Zhao, Chuanchuan [1 ]
You, Jinguo [1 ,2 ]
Wen, Xinxian [1 ]
Li, Xiaowu [1 ,2 ]
机构
[1] Kunming Univ Sci & Technol, Fac Informat Engn & Automat, Kunming 650504, Yunnan, Peoples R China
[2] Comp Technol Applicat Key Lab Yunnan Prov, Kunming 650504, Yunnan, Peoples R China
关键词
recommendation systems; interactive sequence; class label; deep bidirectional LSTM; self-attention; item similarity; MATRIX FACTORIZATION; SYSTEMS;
D O I
10.3390/e22080870
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Recent years have seen a surge in approaches that combine deep learning and recommendation systems to capture user preference or item interaction evolution over time. However, the most related work only consider the sequential similarity between the items and neglects the item content feature information and the impact difference of interacted items on the next items. This paper introduces the deep bidirectional long short-term memory (LSTM) and self-attention mechanism into the sequential recommender while fusing the information of item sequences and contents. Specifically, we deal with the issues in a three-pronged attack: the improved item embedding, weight update, and the deep bidirectional LSTM preference learning. First, the user-item sequences are embedded into a low-dimensional item vector space representation via Item2vec, and the class label vectors are concatenated for each embedded item vector. Second, the embedded item vectors learn different impact weights of each item to achieve item awareness via self-attention mechanism; the embedded item vectors and corresponding weights are then fed into the bidirectional LSTM model to learn the user preference vectors. Finally, the top similar items in the preference vector space are evaluated to generate the recommendation list for users. By conducting comprehensive experiments, we demonstrate that our model outperforms the traditional recommendation algorithms on Recall@20 and Mean Reciprocal Rank (MRR@20).
引用
收藏
页数:14
相关论文
共 50 条
  • [41] A Deep Learning Approach Combining CNN and Bi-LSTM with SVM Classifier for Arabic Sentiment Analysis
    Alharbi, Omar
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2021, 12 (06) : 165 - 172
  • [42] Water quality assessment of a river using deep learning Bi-LSTM methodology: forecasting and validation
    Khullar, Sakshi
    Singh, Nanhey
    ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, 2022, 29 (09) : 12875 - 12889
  • [43] Water quality assessment of a river using deep learning Bi-LSTM methodology: forecasting and validation
    Sakshi Khullar
    Nanhey Singh
    Environmental Science and Pollution Research, 2022, 29 : 12875 - 12889
  • [44] A novel Xi’an drum music generation method based on Bi-LSTM deep reinforcement learning
    Peng Li
    Tian-mian Liang
    Yu-mei Cao
    Xiao-ming Wang
    Xiao-jun Wu
    Lin-yi Lei
    Applied Intelligence, 2024, 54 : 80 - 94
  • [45] A knowledge centric hybridized approach for crime classification incorporating deep bi-LSTM neural network
    Deepak, Gerard
    Rooban, S.
    Santhanavijayan, A.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (18) : 28061 - 28085
  • [46] 基于Bi-LSTM的结构变形预测
    王亚飞
    韩静
    郭凰
    廖聪
    王立新
    计算机系统应用, 2021, 30 (11) : 304 - 309
  • [47] Sandstorm Detection Using Attention Bi-LSTM UNet
    Amira S. Mahmoud
    Rasha M. El-Morshedy
    Mohamed R. Metwalli
    Marwa S. Mostafa
    Journal of the Indian Society of Remote Sensing, 2025, 53 (4) : 1065 - 1076
  • [48] A knowledge centric hybridized approach for crime classification incorporating deep bi-LSTM neural network
    Gerard Deepak
    S. Rooban
    A. Santhanavijayan
    Multimedia Tools and Applications, 2021, 80 : 28061 - 28085
  • [49] Smart Contract Classification With a Bi-LSTM Based Approach
    Tian, Gang
    Wang, Qibo
    Zhao, Yi
    Guo, Lantian
    Sun, Zhonglin
    Lv, Liangyu
    IEEE ACCESS, 2020, 8 : 43806 - 43816
  • [50] Depth Inversion of Coastal Waters Based on Bi-LSTM
    Pan Xinliang
    Yang Renhui
    Jiang Tao
    Sui Baikai
    Liu Chenxi
    Zhang Zhen
    ACTA OPTICA SINICA, 2021, 41 (10)