Journal of Beijing Normal University, Volume. 61, Issue 3, 307(2025)

Multimodal recommendation with semantic graph enhancement and adaptive feature completion

CHAOMU Rilige1,2, HE Mingxin1,2, and MA Liyan3、*
Author Affiliations
  • 1Key Laboraory of Ethnic Language Intelligent Analysis and Security Governance, Ministry of Education, Minzu University of China, Beijing, China
  • 2School of Information Engineering, Minzu University of China, Beijing, China
  • 3School of Computer Engineering and Science, Shanghai University, Shanghai, China
  • show less

    A multimodal recommendation model that integrates high-order semantic enhancement with adaptive modal feature fusion (MMSAF) is proposed. The model employs graph convolutional neural network (GCNN) to perform high-order semantic enhancement, enabling the capture of deeper associations between users and items, thereby more accurately reflecting users' complex preferences. The effectiveness and applicability of this model are validated. An adaptive modality fusion mechanism is introduced to dynamically adjust weights of modal features based on their relative importance in different contexts, enabling flexible adaptation to diverse user preferences. Experimental results demonstrate that MMSAF outperforms existing mainstream methods across multiple benchmark datasets in terms of recommendation accuracy and generalization capability.

    Tools

    Get Citation

    Copy Citation Text

    CHAOMU Rilige, HE Mingxin, MA Liyan. Multimodal recommendation with semantic graph enhancement and adaptive feature completion[J]. Journal of Beijing Normal University, 2025, 61(3): 307

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: Apr. 9, 2025

    Accepted: Aug. 21, 2025

    Published Online: Aug. 21, 2025

    The Author Email: MA Liyan (liyanma@shu.edu.cn)

    DOI:10.12202/j.0476-0301.2025052

    Topics