TY - GEN
T1 - Sequential Recommendation with Latent Relation Information
AU - Zhang, Jiongmin
AU - Liu, Ao
AU - Yang, Xing
AU - Qian, Ying
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Sequential recommendation has attracted a lot of research due to the great value it has shown in online applications. Recently, relation information in sequences has become the focus of sequential recommendation, as it can reflect the re-lationships between items and the long-term interest tendencies of users. However, existing models are largely based directly on user-item interaction and fail to make effective use of the latent relation information. To address this problem, we propose a method to integrate global relation information into the model through the creation of item and user graphs. Furthermore, we propose a graph convolutional network-based relation information extraction module that alleviates the sparsity problem in sequence data. Combining these two designs, we propose a model named SRLRI for the sequential recommendation. Experiments on five real datasets demonstrate its superiority over existing state-of-the-art baselines.
AB - Sequential recommendation has attracted a lot of research due to the great value it has shown in online applications. Recently, relation information in sequences has become the focus of sequential recommendation, as it can reflect the re-lationships between items and the long-term interest tendencies of users. However, existing models are largely based directly on user-item interaction and fail to make effective use of the latent relation information. To address this problem, we propose a method to integrate global relation information into the model through the creation of item and user graphs. Furthermore, we propose a graph convolutional network-based relation information extraction module that alleviates the sparsity problem in sequence data. Combining these two designs, we propose a model named SRLRI for the sequential recommendation. Experiments on five real datasets demonstrate its superiority over existing state-of-the-art baselines.
UR - https://www.scopus.com/pages/publications/85169619459
U2 - 10.1109/IJCNN54540.2023.10191450
DO - 10.1109/IJCNN54540.2023.10191450
M3 - 会议稿件
AN - SCOPUS:85169619459
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - IJCNN 2023 - International Joint Conference on Neural Networks, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Joint Conference on Neural Networks, IJCNN 2023
Y2 - 18 June 2023 through 23 June 2023
ER -