Combination of Unified Embedding Model and Observed Features for Knowledge Graph Completion

TL;DR

This paper presents a unified framework combining embedding models and observed features for knowledge graph completion, improving prediction accuracy and rule evaluation speed.

Contribution

It unifies state-of-the-art embedding models, interprets them as translation-based, and integrates rule evaluation with observed features for enhanced link prediction.

Findings

Outperforms existing models in link prediction accuracy

Faster rule evaluation compared to traditional methods

Effective integration of embedding and observed features

Abstract

Knowledge graphs are useful for many artificial intelligence tasks but often have missing data. Hence, a method for completing knowledge graphs is required. Existing approaches include embedding models, the Path Ranking Algorithm, and rule evaluation models. However, these approaches have limitations. For example, all the information is mixed and difficult to interpret in embedding models, and traditional rule evaluation models are basically slow. In this paper, we provide an integrated view of various approaches and combine them to compensate for their limitations. We first unify state-of-the-art embedding models, such as ComplEx and TorusE, reinterpreting them as a variant of translation-based models. Then, we show that these models utilize paths for link prediction and propose a method for evaluating rules based on this idea. Finally, we combine an embedding model and observed feature models to predict missing triples. This is possible because all of these models utilize paths. We also conduct experiments, including link prediction tasks, with standard datasets to evaluate our method and framework. The experiments show that our method can evaluate rules faster than traditional methods and that our framework outperforms state-of-the-art models in terms of link prediction.