STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systems

被引:0
|
作者
Zhang, Jiani [1 ]
Shi, Xingjian [2 ]
Zhao, Shenglin [3 ]
King, Irwin [1 ]
机构
[1] Chinese Univ Hong Kong, Hong Kong, Peoples R China
[2] Hong Kong Univ Sci & Technol, Hong Kong, Peoples R China
[3] Tencent, Youtu Lab, Shenzhen, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose a new STAcked and Reconstructed Graph Convolutional Networks (STAR-GCN) architecture to learn node representations for boosting the performance in recommender systems, especially in the cold start scenario. STAR-GCN employs a stack of GCN encoder-decoders combined with intermediate supervision to improve the final prediction performance. Unlike the graph convolutional matrix completion model with one-hot encoding node inputs, our STAR-GCN learns low-dimensional user and item latent factors as the input to restrain the model space complexity. Moreover, our STAR-GCN can produce node embeddings for new nodes by reconstructing masked input node embeddings, which essentially tackles the cold start problem. Furthermore, we discover a label leakage issue when training GCN-based models for link prediction tasks and propose a training strategy to avoid the issue. Empirical results on multiple rating prediction benchmarks demonstrate our model achieves state-of-the-art performance in four out of five real-world datasets and significant improvements in predicting ratings in the cold start scenario. The code implementation is available in https://github.com/jennyzhang0215/STAR-GCN.
引用
收藏
页码:4264 / 4270
页数:7
相关论文
共 50 条
  • [1] Neighborhood Graph Convolutional Networks for Recommender Systems
    Liu, Tingting
    Wei, Chenghao
    Song, Baoyan
    Sun, Ruonan
    Yang, Hongxin
    Wan, Ming
    Li, Dong
    Li, Xiaoguang
    ADVANCES IN NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY, ICNC-FSKD 2022, 2023, 153 : 274 - 284
  • [2] Knowledge Graph Convolutional Networks for Recommender Systems
    Wang, Hongwei
    Zhao, Miao
    Xie, Xing
    Li, Wenjie
    Guo, Minyi
    WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019), 2019, : 3307 - 3313
  • [3] HeteGraph: graph learning in recommender systems via graph convolutional networks
    Dai Hoang Tran
    Quan Z. Sheng
    Wei Emma Zhang
    Abdulwahab Aljubairy
    Munazza Zaib
    Salma Abdalla Hamad
    Nguyen H. Tran
    Nguyen Lu Dang Khoa
    Neural Computing and Applications, 2023, 35 : 13047 - 13063
  • [4] HeteGraph: graph learning in recommender systems via graph convolutional networks
    Tran, Dai Hoang
    Sheng, Quan Z.
    Zhang, Wei Emma
    Aljubairy, Abdulwahab
    Zaib, Munazza
    Hamad, Salma Abdalla
    Tran, Nguyen H.
    Khoa, Nguyen Lu Dang
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (18): : 13047 - 13063
  • [5] Structured Graph Convolutional Networks with Stochastic Masks for Recommender Systems
    Chen, Huiyuan
    Wang, Lan
    Lin, Yusan
    Yeh, Chin-Chia Michael
    Wang, Fei
    Yang, Hao
    SIGIR '21 - PROCEEDINGS OF THE 44TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2021, : 614 - 623
  • [6] Graph Convolutional Network for Recommender Systems
    Ge Y.
    Chen S.-C.
    Ruan Jian Xue Bao/Journal of Software, 2020, 31 (04): : 1101 - 1112
  • [7] Graph Convolutional Embeddings for Recommender Systems
    Duran, Paula G.
    Karatzoglou, Alexandros
    Vitria, Jordi
    Xin, Xin
    Arapakis, Ioannis
    IEEE ACCESS, 2021, 9 : 100173 - 100184
  • [8] Graph Convolutional Neural Networks for Web-Scale Recommender Systems
    Ying, Rex
    He, Ruining
    Chen, Kaifeng
    Eksombatchai, Pong
    Hamilton, William L.
    Leskovec, Jure
    KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, : 974 - 983
  • [9] Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
    Min, Yimeng
    Wenkel, Frederik
    Wolf, Guy
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [10] Fault detection in pipelines with graph convolutional networks (GCN) method
    Sahin, Ersin
    Yuce, Hueseyin
    JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, 2024, 40 (01): : 673 - 684