Biomedical knowledge graph verification with multitask learning architectures

Abstract

Objective

Large-scale biomedical KGs, typically constructed using automated entity-relation extraction methods from vast amounts of textual documents, often contain erroneous biomedical triplets, which raises concerns about their quality. Using such noisy KGs in downstream applications can compromise the validity of biomedical research and lead to inaccurate conclusions. This study aims to design an effective knowledge graph verification (KGV) method to determine the correctness of triplets in biomedical KGs, enabling the removal of erroneous triplets identified through the proposed method.

Methods

We propose a multitask-learning-based KGV (referred to as the MTL-KGV) method, which includes two key stages: 1) KG embedding (KGE) learning and (2) triplet classification model learning. In addition, we explore three types of multitask learning (MTL) architectures—hard parameter sharing (HPS), multi-gate mixture-of-experts (MMoE), and customized gate control (CGC)—for triplet classification model learning.

Results

Using SemMedDB as a data source to construct a large-scale KG for KGE training and a dataset of 6,427 biomedical triplets annotated by a domain expert, we empirically evaluate the effectiveness of our proposed MTL-KGV method by comparing it to several benchmark methods. Our evaluation results indicate that all three versions of our proposed MTL-KGV method consistently outperform the benchmark methods. Moreover, our proposed method with the MMoE multitask learning architecture emerges as the most effective for detecting erroneous biomedical triplets.

Conclusion

This work contributes to KGV research by introducing a multitask learning framework tailored for KGV. The proposed MTL-KGV method improves the quality of biomedical KGs, thereby supporting downstream applications and advancing biomedical research that relies on these biomedical KGs.