Reasoning Over Paths via Knowledge Base Completion

TL;DR

This paper presents a method for reasoning over paths in large knowledge graphs by using learned embeddings from a knowledge base completion model, effectively ranking and discovering plausible paths in biomedical literature.

Contribution

It introduces a simple, compositional approach to automatically build and rank paths between entities using KBC models, validated on biomedical literature.

Findings

Reconstructed the highest ranking path 60% of the time within top 10 paths

Achieved 49% mean average precision in path ranking

Successfully identified plausible paths not explicitly in the knowledge graph

Abstract

Reasoning over paths in large scale knowledge graphs is an important problem for many applications. In this paper we discuss a simple approach to automatically build and rank paths between a source and target entity pair with learned embeddings using a knowledge base completion model (KBC). We assembled a knowledge graph by mining the available biomedical scientific literature and extracted a set of high frequency paths to use for validation. We demonstrate that our method is able to effectively rank a list of known paths between a pair of entities and also come up with plausible paths that are not present in the knowledge graph. For a given entity pair we are able to reconstruct the highest ranking path 60% of the time within the the top 10 ranked paths and achieve 49% mean average precision. Our approach is compositional since any KBC model that can produce vector representations of entities can be used.