Type-Constrained Representation Learning in Knowledge Graphs

TL;DR

This paper explores how incorporating type-constraints into latent variable models enhances knowledge graph completion, especially with limited model complexity, and proposes a local closed-world assumption to handle incomplete or fuzzy type information.

Contribution

It introduces a method to integrate type-constraints into latent variable models for knowledge graphs and demonstrates significant improvements in link prediction accuracy.

Findings

Type-constraints improve link prediction by up to 77%.

Benefits are most notable with low model complexity.

Local closed-world assumption helps when type data is incomplete or fuzzy.

Abstract

Large knowledge graphs increasingly add value to various applications that require machines to recognize and understand queries and their semantics, as in search or question answering systems. Latent variable models have increasingly gained attention for the statistical modeling of knowledge graphs, showing promising results in tasks related to knowledge graph completion and cleaning. Besides storing facts about the world, schema-based knowledge graphs are backed by rich semantic descriptions of entities and relation-types that allow machines to understand the notion of things and their semantic relationships. In this work, we study how type-constraints can generally support the statistical modeling with latent variable models. More precisely, we integrated prior knowledge in form of type-constraints in various state of the art latent variable approaches. Our experimental results show that prior knowledge on relation-types significantly improves these models up to 77% in link-prediction tasks. The achieved improvements are especially prominent when a low model complexity is enforced, a crucial requirement when these models are applied to very large datasets. Unfortunately, type-constraints are neither always available nor always complete e.g., they can become fuzzy when entities lack proper typing. We show that in these cases, it can be beneficial to apply a local closed-world assumption that approximates the semantics of relation-types based on observations made in the data.