A Re-evaluation of Knowledge Graph Completion Methods

TL;DR

This paper critically re-evaluates knowledge graph completion methods, identifying evaluation biases in recent studies and proposing a robust protocol to ensure fair comparison of model performances.

Contribution

It introduces a new, robust evaluation protocol for KGC methods and demonstrates its effectiveness through extensive experiments on existing models.

Findings

Previous high performances were inflated due to biased evaluation protocols

The new protocol provides more reliable and consistent performance assessments

Reproducible code is publicly available for further research

Abstract

Knowledge Graph Completion (KGC) aims at automatically predicting missing links for large-scale knowledge graphs. A vast number of state-of-the-art KGC techniques have got published at top conferences in several research fields, including data mining, machine learning, and natural language processing. However, we notice that several recent papers report very high performance, which largely outperforms previous state-of-the-art methods. In this paper, we find that this can be attributed to the inappropriate evaluation protocol used by them and propose a simple evaluation protocol to address this problem. The proposed protocol is robust to handle bias in the model, which can substantially affect the final results. We conduct extensive experiments and report the performance of several existing methods using our protocol. The reproducible code has been made publicly available