Two-view Graph Neural Networks for Knowledge Graph Completion
This work addresses knowledge graph completion for AI applications, but it is incremental as it builds on existing GNN methods with a novel two-view approach.
The authors tackled knowledge graph completion by proposing WGE, a graph neural network model that learns from entity- and relation-focused graphs, and it outperformed strong baselines on seven benchmark datasets.
We present an effective graph neural network (GNN)-based knowledge graph embedding model, which we name WGE, to capture entity- and relation-focused graph structures. Given a knowledge graph, WGE builds a single undirected entity-focused graph that views entities as nodes. WGE also constructs another single undirected graph from relation-focused constraints, which views entities and relations as nodes. WGE then proposes a GNN-based architecture to better learn vector representations of entities and relations from these two single entity- and relation-focused graphs. WGE feeds the learned entity and relation representations into a weighted score function to return the triple scores for knowledge graph completion. Experimental results show that WGE outperforms strong baselines on seven benchmark datasets for knowledge graph completion.