AsyncET: Asynchronous Learning for Knowledge Graph Entity Typing with Auxiliary Relations

TL;DR

AsyncET introduces multiple auxiliary relations and an asynchronous learning scheme to enhance knowledge graph entity typing, significantly improving performance, model size, and efficiency over existing methods.

Contribution

The paper proposes a novel approach using multiple auxiliary relations and asynchronous learning for KGET, improving expressiveness and efficiency over prior single-relation methods.

Findings

Substantial performance improvement on KGET datasets

Efficient model with smaller size and lower time complexity

Effective modeling of diverse entity-type patterns

Abstract

Knowledge graph entity typing (KGET) is a task to predict the missing entity types in knowledge graphs (KG). Previously, KG embedding (KGE) methods tried to solve the KGET task by introducing an auxiliary relation, 'hasType', to model the relationship between entities and their types. However, a single auxiliary relation has limited expressiveness for diverse entity-type patterns. We improve the expressiveness of KGE methods by introducing multiple auxiliary relations in this work. Similar entity types are grouped to reduce the number of auxiliary relations and improve their capability to model entity-type patterns with different granularities. With the presence of multiple auxiliary relations, we propose a method adopting an Asynchronous learning scheme for Entity Typing, named AsyncET, which updates the entity and type embeddings alternatively to keep the learned entity embedding up-to-date and informative for entity type prediction. Experiments are conducted on two commonly used KGET datasets to show that the performance of KGE methods on the KGET task can be substantially improved by the proposed multiple auxiliary relations and asynchronous embedding learning. Furthermore, our method has a significant advantage over state-of-the-art methods in model sizes and time complexity.