[1]ZHU Jinxia,MENG Xiangfu,XING Changzheng,et al.Light graph convolutional collaborative filtering recommendation approach incorporating social relationships[J].CAAI Transactions on Intelligent Systems,2022,17(4):788-797.[doi:10.11992/tis.202107031]
Copy
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
17
Number of periods:
2022 4
Page number:
788-797
Column:
学术论文—人工智能基础
Public date:
2022-07-05
- Title:
-
Light graph convolutional collaborative filtering recommendation approach incorporating social relationships
- Author(s):
-
ZHU Jinxia; MENG Xiangfu; XING Changzheng; SUN Dewei; XUE Qi; GUAN Junbo
-
School of Electronics and Information Engineering, Liaoning Technical University, Huludao 125105, China
-
- Keywords:
-
collaborative filtering; graph convolution network; attention mechanism; social relationships; recommendation system; implicit negative feedback; graph embedding; user preference
- CLC:
-
TP311
- DOI:
-
10.11992/tis.202107031
- Abstract:
-
Graph convolutional network (GCN) has rapidly developed due to their powerful modeling capability. However, much of the research up to now has directly inherited the complex design of GCN (e.g., feature transformation and nonlinear activation), which lacks thorough ablation analysis on GCN. Additionally, implicit feedback is not fully utilized, and data sparsity is not well resolved, which are also shortcomings of current recommendation algorithms. This paper proposes a light graph convolutional collaborative filtering recommendation approach that incorporates social relationships to address such problems (F-LightGCCF). In GCN, the model abandons the design of feature transformation and nonlinear activation. Then it can generate a series of intermediate feedback from users’ implicit negative feedback by taking advantage of social networking, improving the utilization of implicit negative feedback. Lastly, the importance of the contribution values of neighboring nodes and the learning vectors of each layer of the graph convolution layer are aggregated separately using the dual attention mechanism. By conducting experiments on two publicly available datasets, the results show that the proposed model outperforms current graph convolutional collaborative filtering algorithms in the recommendation.