CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding

TL;DR

CORE introduces a novel method for entity type prediction in knowledge graphs by combining complex space embeddings with regression, outperforming existing methods on standard datasets.

Contribution

It proposes a new KG entity type prediction approach using complex space regression and embedding, integrating RotatE and ComplEx models for improved accuracy.

Findings

CORE outperforms benchmark methods on key datasets.

The method effectively links entity and type spaces via complex regression.

Joint optimization enhances embedding and regression performance.

Abstract

Entity type prediction is an important problem in knowledge graph (KG) research. A new KG entity type prediction method, named CORE (COmplex space Regression and Embedding), is proposed in this work. The proposed CORE method leverages the expressive power of two complex space embedding models; namely, RotatE and ComplEx models. It embeds entities and types in two different complex spaces using either RotatE or ComplEx. Then, we derive a complex regression model to link these two spaces. Finally, a mechanism to optimize embedding and regression parameters jointly is introduced. Experiments show that CORE outperforms benchmarking methods on representative KG entity type inference datasets. Strengths and weaknesses of various entity type prediction methods are analyzed.