Improving Graph Neural Network Models in Link Prediction Task via A Policy-Based Training Method

被引:1
作者
Shang, Yigeng [1 ]
Hao, Zhigang [1 ]
Yao, Chao [1 ,2 ]
Li, Guoliang [1 ,3 ,4 ,5 ]
机构
[1] Huazhong Agr Univ, Coll Informat, Wuhan 430070, Peoples R China
[2] Wuhan Vocat Coll Software & Engn, Sch Informat, Wuhan 430205, Peoples R China
[3] Huazhong Agr Univ, Key Lab Smart Farming Agr Anim, Wuhan 430070, Peoples R China
[4] Huazhong Agr Univ, Hubei Engn Technol Res Ctr Agr Big Data, Wuhan 430070, Peoples R China
[5] Minist Educ, Engn Res Ctr Intelligent Technol Agr, Wuhan 430070, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 01期
关键词
graph neural network; link prediction; deep learning; reinforcement learning;
D O I
10.3390/app13010297
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Graph neural network (GNN), as a widely used deep learning model in processing graph-structured data, has attracted numerous studies to apply it in the link prediction task. In these studies, observed edges in a network are utilized as positive samples, and unobserved edges are randomly sampled as negative ones. However, there are problems in randomly sampling unobserved edges as negative samples. First, some unobserved edges are missing edges that are existing edges in the network. Second, some unobserved edges can be easily distinguished from the observed edges, which cannot contribute sufficiently to the prediction task. Therefore, using the randomly sampled unobserved edges directly as negative samples is difficult to make GNN models achieve satisfactory prediction performance in the link prediction task. To address this issue, we propose a policy-based training method (PbTRM) to improve the quality of negative samples. In the proposed PbTRM, a negative sample selector generates the state vectors of the randomly sampled unobserved edges and determines whether to select them as negative samples. We perform experiments with three GNN models on two standard datasets. The results show that the proposed PbTRM can enhance the prediction performance of GNN models in the link prediction task.
引用
收藏
页数:12
相关论文
共 25 条
[1]   Friends and neighbors on the Web [J].
Adamic, LA ;
Adar, E .
SOCIAL NETWORKS, 2003, 25 (03) :211-230
[2]   Evolution of the social network of scientific collaborations [J].
Barabási, AL ;
Jeong, H ;
Néda, Z ;
Ravasz, E ;
Schubert, A ;
Vicsek, T .
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2002, 311 (3-4) :590-614
[3]  
Bruna J., 2014, arXiv
[4]  
Fey M., 2019, ARXIV
[5]  
Grover A, 2019, PR MACH LEARN RES, V97
[6]   Multi-Scale Variational Graph AutoEncoder for Link Prediction [J].
Guo, Zhihao ;
Wang, Feng ;
Yao, Kaixuan ;
Liang, Jiye ;
Wang, Zhiqiang .
WSDM'22: PROCEEDINGS OF THE FIFTEENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2022, :334-342
[7]  
Hamilton WL, 2017, ADV NEUR IN, V30
[8]  
Jaccard P., 1901, B SOC VAUD SCI NAT, V37, P241, DOI DOI 10.5169/SEALS-266440
[9]  
Kipf T. N., 2016, ARXIV
[10]   Link prediction techniques, applications, and performance: A survey [J].
Kumar, Ajay ;
Singh, Shashank Sheshar ;
Singh, Kuldeep ;
Biswas, Bhaskar .
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2020, 553