Learning Heterogeneous Graph Embedding with Metapath-Based Aggregation for Link Prediction
-
Published:2023-01-21
Issue:3
Volume:11
Page:578
-
ISSN:2227-7390
-
Container-title:Mathematics
-
language:en
-
Short-container-title:Mathematics
Author:
Zhang Chengdong1, Li Keke1, Wang Shaoqing1, Zhou Bin1, Wang Lei1, Sun Fuzhen1
Affiliation:
1. School of Computer Science and Technology, Shandong University of Technology, Zibo 255091, China
Abstract
Along with the growth of graph neural networks (GNNs), many researchers have adopted metapath-based GNNs to handle complex heterogeneous graph embedding. The conventional definition of a metapath only distinguishes whether there is a connection between nodes in the network schema, where the type of edge is ignored. This leads to inaccurate node representation and subsequently results in suboptimal prediction performance. In heterogeneous graphs, a node can be connected by multiple types of edges. In fact, each type of edge represents one kind of scene. The intuition is that if the embedding of nodes is trained under different scenes, the complete representation of nodes can be obtained by organically combining them. In this paper, we propose a novel definition of a metapath whereby the edge type, i.e., the relation between nodes, is integrated into it. A heterogeneous graph can be considered as the compound of multiple relation subgraphs from the view of a novel metapath. In different subgraphs, the embeddings of a node are separately trained by encoding and aggregating the neighbors of the intrapaths, which are the instance levels of a novel metapath. Then, the final embedding of the node is obtained by the use of the attention mechanism which aggregates nodes from the interpaths, which is the semantic level of the novel metapaths. Link prediction is a downstream task by which to evaluate the effectiveness of the learned embeddings. We conduct extensive experiments on three real-world heterogeneous graph datasets for link prediction. The empirical results show that the proposed model outperforms the state-of-the-art baselines; in particular, when comparing it to the best baseline, the F1 metric is increased by 10.35% over an Alibaba dataset.
Funder
Shandong Provincial Natural Science Foundation, China
Subject
General Mathematics,Engineering (miscellaneous),Computer Science (miscellaneous)
Reference43 articles.
1. Amigó, E., Castells, P., Gonzalo, J., Carterette, B., Culpepper, J.S., and Kazai, G. (2022, January 11–15). BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction. Proceedings of the SIGIR’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain. 2. Yadati, N., Nitin, V., Nimishakavi, M., Yadav, P., Louis, A., and Talukdar, P. (2020, January 19–23). NHP: Neural Hypergraph Link Prediction. Proceedings of the 29th ACM International Conference on Information & Knowledge Management, CIKM’20, Online. 3. Amigó, E., Castells, P., Gonzalo, J., Carterette, B., Culpepper, J.S., and Kazai, G. (2022, January 11–15). DH-HGCN: Dual Homogeneity Hypergraph Convolutional Network for Multiple Social Recommendations. Proceedings of the SIGIR’22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain. 4. Perozzi, B., Al-Rfou, R., and Skiena, S. (2014, January 24–27). Deepwalk: Online learning of social representations. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA. 5. Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., and Mei, Q. (2015, January 18–22). LINE: Large-Scale Information Network Embedding. Proceedings of the 24th International Conference on World Wide Web, Florence, Italy.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|