Abstract
Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning. Inspired by the success of graph convolutional networks (GCN) in modeling graph data, we propose a unified GCN framework, named TransGCN, to address this task, in which relation and entity embeddings are learned simultaneously. To handle heterogeneous relations in KGs, we introduce a novel way of representing heterogeneous neighborhood by introducing transformation assumptions on the relationship between the subject, the relation, and the object of a triple. Specifically, a relation is treated as a transformation operator transforming a head entity to a tail entity. Both translation assumption in TransE and rotation assumption in RotatE are explored in our framework. Additionally, instead of only learning entity embeddings in the convolution-based encoder while learning relation embeddings in the decoder as done by the state-of-art models, e.g., R-GCN, the TransGCN framework trains relation embeddings and entity embeddings simultaneously during the graph convolution operation, thus having fewer parameters compared with R-GCN. Experiments show that our models outperform the-state-of-arts methods on both FB15K-237 and WN18RR.
Original language | English |
---|---|
Title of host publication | K-CAP '19 |
Subtitle of host publication | Proceedings of the 10th International Conference on Knowledge Capture |
Publisher | Association for Computing Machinery (ACM) |
Pages | 131–138 |
Number of pages | 8 |
ISBN (Electronic) | 978-1-4503-7008-0 |
DOIs | |
Publication status | Published - 23 Sept 2019 |
Event | 10th International Conference on Knowledge Capture, K-CAP 2019 - Marina Del Rey, United States Duration: 19 Nov 2019 → 21 Nov 2019 |
Publication series
Name | K-CAP 2019 - Proceedings of the 10th International Conference on Knowledge Capture |
---|
Conference
Conference | 10th International Conference on Knowledge Capture, K-CAP 2019 |
---|---|
Country/Territory | United States |
City | Marina Del Rey |
Period | 19/11/19 → 21/11/19 |
Bibliographical note
Publisher Copyright:© 2019 ACM.
Keywords
- Graph convolutional network
- Knowledge graph embedding
- Link prediction
- Neighborhood
- Transformation assumption