Modeling Relational Data with Graph Convolutional Networks, Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling, 2017Extended Semantic Web Conference (ESWC)DOI: 10.1007/978-3-319-93417-4_29 - Introduces Relational Graph Convolutional Networks (R-GCNs) for modeling knowledge graphs, detailing relation-specific transformations and parameter regularization techniques.
Composition-based Multi-Relational Graph Convolutional Networks, Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Partha Talukdar, 2020International Conference on Learning Representations (ICLR) 2020DOI: 10.48550/arXiv.1911.03082 - Presents Composition-based Multi-Relational Graph Convolutional Networks (CompGCN), using compositional operators to learn entity and relation embeddings.
Graph Neural Networks for Knowledge Graph Completion: An Overview, Chengjin Zhang, Fan Zhou, Pengyuan Zhang, Yuqing Xia, Cheng Shi, and Jianlong Tan, 2020Journal of Artificial Intelligence Research, Vol. 67 (AI Access Foundation)DOI: 10.1613/jair.1.12177 - Comprehensive overview of Graph Neural Networks applied to knowledge graph completion, discussing various architectures and tasks.
Heterogeneous Graph Attention Network, Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Yanfang Ye, Peng Cui, Philip S. Yu, 2019The Web Conference (WWW) (ACM)DOI: 10.1145/3308558.3313562 - Proposes the Heterogeneous Graph Attention Network (HAN), which incorporates attention mechanisms for hierarchical aggregation on heterogeneous graphs.