TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
This addresses the limitation of existing knowledge graph embedding models in handling relational diversity, offering a novel approach for tasks like entity alignment and link prediction.
The paper tackles the problem of capturing diverse relational structures in knowledge graphs by proposing TransEdge, an edge-centric embedding model that contextualizes relation representations for specific entity pairs, achieving state-of-the-art results on entity alignment and competitive performance on link prediction.
Learning knowledge graph (KG) embeddings has received increasing attention in recent years. Most embedding models in literature interpret relations as linear or bilinear mapping functions to operate on entity embeddings. However, we find that such relation-level modeling cannot capture the diverse relational structures of KGs well. In this paper, we propose a novel edge-centric embedding model TransEdge, which contextualizes relation representations in terms of specific head-tail entity pairs. We refer to such contextualized representations of a relation as edge embeddings and interpret them as translations between entity embeddings. TransEdge achieves promising performance on different prediction tasks. Our experiments on benchmark datasets indicate that it obtains the state-of-the-art results on embedding-based entity alignment. We also show that TransEdge is complementary with conventional entity alignment methods. Moreover, it shows very competitive performance on link prediction.