Logo image
Back
A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment
Conference paper   Peer reviewed

A Vectorized Relational Graph Convolutional Network for Multi-Relational Network Alignment

Rui Ye, Xin Li, Yujie Fang, Hongyu Zang and Mingzhong Wang
Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp.4135-4141
International Joint Conference on Artificial Intelligence (IJCAI-19), 28th (Macao, China, 10-Aug-2019–16-Aug-2019)
International Joint Conference on Artificial Intelligence
2019
DOI: https://doi.org/10.24963/ijcai.2019/574
url
https://doi.org/10.24963/ijcai.2019/574View
Published Version

Abstract

machine learning relational learning knowledge representation and reasoning knowledge representation and decision utility theory
Alignment of multiple multi-relational networks, such as knowledge graphs, is vital for AI applications. Different from the conventional alignment models, we apply the graph convolutional network (GCN) to achieve more robust network embedding for the alignment task. In comparison with existing GCNs which cannot fully utilize multi-relation information, we propose a vectorized relational graph convolutional network (VR-GCN) to learn the embeddings of both graph entities and relations simultaneously for multi-relational networks. The role discrimination and translation property of knowledge graphs are adopted in the convolutional process. Thereafter, AVR-GCN, the alignment framework based on VR-GCN, is developed for multi-relational network alignment tasks. Anchors are used to supervise the objective function which aims at minimizing the distances between anchors, and to generate new cross-network triplets to build a bridge between different knowledge graphs at the level of triplet to improve the performance of alignment. Experiments on real-world datasets show that the proposed solutions outperform the state-of-the-art methods in terms of network embedding, entity alignment, and relation alignment.

Details

Metrics

143 Record Views
Logo image