A Method to Learn Embedding of a Probabilistic Medical Knowledge Graph: Algorithm Development

TL;DR

This paper introduces PrTransH, an algorithm for embedding probabilistic medical knowledge graphs from EMR data, addressing uncertainty in triplet correctness and outperforming existing methods in link prediction.

Contribution

It develops the first method to learn and verify embeddings on probabilistic knowledge graphs, enhancing TransH with probabilistic and background knowledge integration.

Findings

PrTransH outperforms TransH in link prediction tasks.

Incorporating triplet probability improves embedding accuracy.

Augmenting data with medical background knowledge enhances performance.

Abstract

This paper proposes an algorithm named as PrTransH to learn embedding vectors from real world EMR data based medical knowledge. The unique challenge in embedding medical knowledge graph from real world EMR data is that the uncertainty of knowledge triplets blurs the border between "correct triplet" and "wrong triplet", changing the fundamental assumption of many existing algorithms. To address the challenge, some enhancements are made to existing TransH algorithm, including: 1) involve probability of medical knowledge triplet into training objective; 2) replace the margin-based ranking loss with unified loss calculation considering both valid and corrupted triplets; 3) augment training data set with medical background knowledge. Verifications on real world EMR data based medical knowledge graph prove that PrTransH outperforms TransH in link prediction task. To the best of our survey, this paper is the first one to learn and verify knowledge embedding on probabilistic knowledge graphs.