# Knowledge Base Completion: Baselines Strike Back

## TL;DR

This paper demonstrates that a well-tuned baseline model can outperform recent complex models in knowledge base completion tasks, questioning the attribution of improvements to architectural innovations.

## Contribution

It shows that hyper-parameter tuning of a simple baseline can surpass recent models, urging a reevaluation of how model performance is assessed in the field.

## Key findings

- Baseline model outperforms recent models on FB15k.
- Hyper-parameter tuning significantly impacts performance.
- Recent architectural improvements may not be the main factor in performance gains.

## Abstract

Many papers have been published on the knowledge base completion task in the past few years. Most of these introduce novel architectures for relation learning that are evaluated on standard datasets such as FB15k and WN18. This paper shows that the accuracy of almost all models published on the FB15k can be outperformed by an appropriately tuned baseline - our reimplementation of the DistMult model. Our findings cast doubt on the claim that the performance improvements of recent models are due to architectural changes as opposed to hyper-parameter tuning or different training objectives. This should prompt future research to re-consider how the performance of models is evaluated and reported.