Relation Prediction via Graph Neural Network in Heterogeneous Information Networks with Missing Type Information

被引:2
作者
Zhang, Han [1 ]
Hao, Yu [1 ]
Cao, Xin [1 ]
Fang, Yixiang [2 ]
Shin, Won-Yong [3 ]
Wang, Wei [4 ]
机构
[1] Univ New South Wales, Kensington, NSW, Australia
[2] Chinese Univ Hong Kong, Shenzhen, Peoples R China
[3] Yonsei Univ, Seoul, South Korea
[4] Hong Kong Univ Sci & Technol, Guangzhou, Peoples R China
来源
PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021 | 2021年
基金
新加坡国家研究基金会;
关键词
Relation prediction; Heterogeneous information network; Graph neural network; Graph representation learning;
D O I
10.1145/3459637.3482384
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Relation prediction is a fundamental task in network analysis which aims to predict the relationship between two nodes. Thus, this differes from the traditional link prediction problem predicting whether a link exists between a pair of nodes, which can be viewed as a binary classification task. However, in the heterogeneous information network (HIN) which contains multiple types of nodes and multiple relations between nodes, the relation prediction task is more challenging. In addition, the HIN might have missing relation types on some edges and missing node types on some nodes, which makes the problem even harder. In this work, we propose RPGNN, a novel relation prediction model based on the graph neural network (GNN) and multi-task learning to solve this problem. Existing GNN models for HIN representation learning usually focus on the node classification/clustering task. They require the type information of all edges and nodes and always learn a weight matrix for each type, thus requiring a large number of learning parameters on HINs with rich schema. In contrast, our model directly encodes and learns relations in HIN and avoids the requirement of type information during message passing in GNN. Hence, our model is more robust to the missing types for the relation prediction task on HINs. The experiments on real HINs show that our model can consistently achieve better performance than several state-of-the-art HIN representation learning methods.
引用
收藏
页码:2517 / 2526
页数:10
相关论文
共 50 条
[21]   ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware Embedding [J].
Zhu, Xiaoyu ;
Yu, Xinzhe ;
Zha, Enze ;
Lin, Shiyang .
IEEE ACCESS, 2025, 13 :44951-44962
[22]   Relation Structure-Aware Heterogeneous Graph Neural Network [J].
Zhu, Shichao ;
Zhou, Chuan ;
Pan, Shirui ;
Zhu, Xingquan ;
Wang, Bin .
2019 19TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2019), 2019, :1534-1539
[23]   Learning accurate neighborhood- and self-information for higher-order relation prediction in Heterogeneous Information Networks [J].
Li, Jie ;
Guo, Xuan ;
Jiao, Pengfei ;
Wang, Wenjun .
NEUROCOMPUTING, 2025, 613
[24]   Exploiting Heterogeneous Graph Neural Networks with LatentWorker/Task Correlation Information for Label Aggregation in Crowdsourcing [J].
Wu, Hanlu ;
Ma, Tengfei ;
Wu, Lingfei ;
Xu, Fangli ;
Ji, Shouling .
ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2022, 16 (02)
[25]   Link Prediction Based on Deep Global Information in Heterogeneous Graph [J].
Qian, Rong ;
Lv, ZongFang ;
Zhou, YuChen ;
Fu, ZiQiang ;
Liu, XiaoYu ;
Zhang, KeJun ;
Ye, ZhongKun .
KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, KSEM 2024, 2024, 14884 :240-254
[26]   DYNAMIC NETWORK REPRESENTATION LEARNING METHOD COMBINING GRAPH NEURAL NETWORKS AND TEMPORAL INFORMATION [J].
Li, Zhixiao .
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2024, 20 (06) :1803-1817
[27]   Industry classification based on supply chain network information using Graph Neural Networks [J].
Wu, Desheng ;
Wang, Quanbin ;
Olson, David L. .
APPLIED SOFT COMPUTING, 2023, 132
[28]   Opinion Leaders for Information Diffusion Using Graph Neural Network in Online Social Networks [J].
Jain, Lokesh ;
Katarya, Rahul ;
Sachdeva, Shelly .
ACM TRANSACTIONS ON THE WEB, 2023, 17 (02)
[29]   Graph neural network and multi-data heterogeneous networks for microbe-disease prediction [J].
Gong, Houwu ;
You, Xiong ;
Jin, Min ;
Meng, Yajie ;
Zhang, Hanxue ;
Yang, Shuaishuai ;
Xu, Junlin .
FRONTIERS IN MICROBIOLOGY, 2022, 13
[30]   InsGNN: Interpretable spatio-temporal graph neural networks via information bottleneck [J].
Fang, Hui ;
Wang, Haishuai ;
Gao, Yang ;
Zhang, Yonggang ;
Bu, Jiajun ;
Han, Bo ;
Lin, Hui .
INFORMATION FUSION, 2025, 119