Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding

Knowledge graphs (KGs) which consist of a large number of triples have become widespread recently, and many knowledge graph embedding (KGE) methods are proposed to embed entities and relations of a KG into continuous vector spaces. Such embedding methods aim at simplifying the operations of conducting various in-KG tasks (e.g., link prediction) and out-of-KG tasks (e.g., question answering), and can be viewed as general solutions for representing KGs. However, existing KGE methods are not applicable to inductive settings, where a model trained on source KGs will be tested on target KGs with entities unseen during model training. Existing works focusing on KGs in inductive settings can only solve the inductive relation prediction task and can not handle other out-of-KG tasks as general as KGE methods, since they don't produce embeddings for entities. In this paper, to achieve inductive knowledge graph embedding, we propose a model MorsE, which doesn't learn embeddings for entities, while learning transferable meta-knowledge that can be used to produce entity embeddings. Such meta-knowledge is modeled by entity-independent modules and learned by meta-learning. Experimental results show that our model significantly outperforms corresponding baselines for in-KG and out-of-KG tasks in inductive settings.