CNN-based Dual-Chain Models for Knowledge Graph Learning

TL;DR

This paper introduces a CNN-based dual-chain model for knowledge graph learning that captures relations directly from embeddings and handles zero-shot problems by incorporating entity descriptions, outperforming existing methods on benchmarks.

Contribution

The paper proposes a novel CNN-based dual-chain model that directly models entity-relation interactions and extends it to handle zero-shot entities using descriptions.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively handles zero-shot entity problems.

Produces domain-consistent results on biomedical data.

Abstract

Knowledge graph learning plays a critical role in integrating domain specific knowledge bases when deploying machine learning and data mining models in practice. Existing methods on knowledge graph learning primarily focus on modeling the relations among entities as translations among the relations and entities, and many of these methods are not able to handle zero-shot problems, when new entities emerge. In this paper, we present a new convolutional neural network (CNN)-based dual-chain model. Different from translation based methods, in our model, interactions among relations and entities are directly captured via CNN over their embeddings. Moreover, a secondary chain of learning is conducted simultaneously to incorporate additional information and to enable better performance. We also present an extension of this model, which incorporates descriptions of entities and learns a second set of entity embeddings from the descriptions. As a result, the extended model is able to effectively handle zero-shot problems. We conducted comprehensive experiments, comparing our methods with 15 methods on 8 benchmark datasets. Extensive experimental results demonstrate that our proposed methods achieve or outperform the state-of-the-art results on knowledge graph learning, and outperform other methods on zero-shot problems. In addition, our methods applied to real-world biomedical data are able to produce results that conform to expert domain knowledge.