Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding

TL;DR

This paper introduces MorsE, a meta-learning based model that learns transferable meta-knowledge for inductive knowledge graph embedding, enabling generalization to unseen entities and outperforming existing methods in various tasks.

Contribution

The paper proposes MorsE, a novel inductive KGE model that learns transferable meta-knowledge without entity embeddings, extending inductive capabilities beyond relation prediction.

Findings

MorsE significantly outperforms baselines in inductive link prediction.

MorsE effectively handles both in-KG and out-of-KG tasks.

Meta-knowledge transfer improves generalization to unseen entities.

Abstract

Knowledge graphs (KGs) consisting 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 simplify the operations of conducting various in-KG tasks (e.g., link prediction) and out-of-KG tasks (e.g., question answering). They 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. They 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 does not learn embeddings for entities but learns 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.