Fast and scalable learning of neuro-symbolic representations of biomedical knowledge

TL;DR

This paper presents a fast, scalable method for learning neuro-symbolic representations of biomedical knowledge graphs, significantly improving classification accuracy and efficiency for biological link prediction tasks.

Contribution

The authors introduce a rapid (under 1 minute) log-linear neural embedding technique that enhances biological relation classification and encodes relation directionality effectively.

Findings

Embedding training time reduced to under 1 minute

Significant improvement in classification metrics (+0.28 F-measure, +0.22 ROC AUC)

Embeddings are more economical and encode relation directionality

Abstract

In this work we address the problem of fast and scalable learning of neuro-symbolic representations for general biological knowledge. Based on a recently published comprehensive biological knowledge graph (Alshahrani, 2017) that was used for demonstrating neuro-symbolic representation learning, we show how to train fast (under 1 minute) log-linear neural embeddings of the entities. We utilize these representations as inputs for machine learning classifiers to enable important tasks such as biological link prediction. Classifiers are trained by concatenating learned entity embeddings to represent entity relations, and training classifiers on the concatenated embeddings to discern true relations from automatically generated negative examples. Our simple embedding methodology greatly improves on classification error compared to previously published state-of-the-art results, yielding a maximum increase of $+0.28$ F-measure and $+0.22$ ROC AUC scores for the most difficult biological link prediction problem. Finally, our embedding approach is orders of magnitude faster to train ($\leq$ 1 minute vs. hours), much more economical in terms of embedding dimensions ($d=50$ vs. $d=512$), and naturally encodes the directionality of the asymmetric biological relations, that can be controlled by the order with which we concatenate the embeddings.