On Inductive Abilities of Latent Factor Models for Relational Learning

TL;DR

This paper investigates the inductive capabilities of latent factor models for relational learning in knowledge graphs through experimental surveys and synthetic tasks, revealing their strengths and weaknesses.

Contribution

It provides an empirical analysis of state-of-the-art models' inductive abilities and suggests new research directions for improvement.

Findings

Models excel at certain atomic relation properties

Identified weaknesses in inter-relational inference

Proposed new research directions for model enhancement

Abstract

Latent factor models are increasingly popular for modeling multi-relational knowledge graphs. By their vectorial nature, it is not only hard to interpret why this class of models works so well, but also to understand where they fail and how they might be improved. We conduct an experimental survey of state-of-the-art models, not towards a purely comparative end, but as a means to get insight about their inductive abilities. To assess the strengths and weaknesses of each model, we create simple tasks that exhibit first, atomic properties of binary relations, and then, common inter-relational inference through synthetic genealogies. Based on these experimental results, we propose new research directions to improve on existing models.