Light dual hypergraph convolution for collaborative filtering

被引:2
|
作者
Jian, Meng [1 ,2 ]
Lang, Langchen [1 ]
Guo, Jingjing [1 ]
Li, Zun [1 ]
Wang, Tuo [1 ]
Wu, Lifang [1 ,2 ]
机构
[1] Faculty of Information Technology, Beijing University of Technology, Beijing,100124, China
[2] Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing,100124, China
关键词
Collaborative filtering;
D O I
10.1016/j.patcog.2024.110596
中图分类号
学科分类号
摘要
Recommender systems filter information to meet users’ personalized interests actively. Existing graph-based models typically extract users’ interests from a heterogeneous interaction graph. They do not distinguish learning between users and items, ignoring the heterogeneous property. In addition, the interaction sparsity and long-tail bias issues still limit the recommendation performance significantly. Fortunately, hidden homogeneous correlations that have a considerable volume can entangle abundant CF signals. In this paper, we propose a light dual hypergraph convolution (LDHC) for collaborative filtering, which designs a hypergraph to involve heterogeneous and homogeneous correlations with more CF signals confronting the challenges. Over the integrated hypergraph, a two-level interest propagation is performed within the heterogeneous interaction graph and between the homogeneous user/item graphs to model users’ interests, where learning on users and items is distinguished and collaborated by the homogeneous propagation. Specifically, hypergraph convolution is lightened by removing unnecessary parameters to propagate users’ interests. Extensive experiments on publicly available datasets demonstrate that the proposed LDHC outperforms the state-of-the-art baselines. © 2024 Elsevier Ltd
引用
收藏
相关论文
共 50 条
  • [21] HGCF: Hyperbolic Graph Convolution Networks for Collaborative Filtering
    Sun, Jianing
    Cheng, Zhaoyue
    Zuberi, Saba
    Perez, Felipe
    Volkovs, Maksims
    PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021), 2021, : 593 - 601
  • [22] EFBH: Collaborative Filtering Model Based on Multi-Hypergraph Encoder
    Yang, Zhe
    Xu, Liangkui
    Zhao, Lei
    IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2024, 70 (01) : 2939 - 2948
  • [23] HyperGraph Convolution Based Attributed HyperGraph Clustering
    Kamhoua, Barakeel Fanseu
    Zhang, Lin
    Ma, Kaili
    Cheng, James
    Li, Bo
    Han, Bo
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 453 - 463
  • [24] Dual Relations Network for Collaborative Filtering
    Ji, Daomin
    Xiang, Zhenglong
    Li, Yuanxiang
    IEEE ACCESS, 2020, 8 : 109747 - 109757
  • [25] Improvement Graph Convolution Collaborative Filtering with Weighted Addition Input
    Tran, Tin T.
    Snasel, Vaclav
    INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2022, PT I, 2022, 13757 : 635 - 647
  • [26] Residual Graph Convolution Collaborative Filtering with Asymmetric neighborhood aggregation
    Wang T.
    Qin J.
    Ma C.
    Neural Computing and Applications, 2024, 36 (22) : 13989 - 14003
  • [27] Collaborative filtering recommendation algorithm based on sparse bilinear convolution
    Zhang, Xiangfeng
    Engineering Intelligent Systems, 2020, 28 (04): : 205 - 214
  • [28] A Lightweight Method of Knowledge Graph Convolution Network for Collaborative Filtering
    Zhang, Xin
    Kuang, Shaohua
    INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS, 2023, 19 (01)
  • [29] Collaborative filtering using dual information sources
    Cho, Jinhyung
    Kwon, Kwiseok
    Park, Yongtae
    IEEE INTELLIGENT SYSTEMS, 2007, 22 (03) : 30 - 38
  • [30] RGCF: Refined graph convolution collaborative filtering with concise and expressive embedding
    Liu, Kang
    Xue, Feng
    Hong, Richang
    INTELLIGENT DATA ANALYSIS, 2022, 26 (02) : 427 - 445