# Revisiting Simple Neural Networks for Learning Representations of Knowledge Graphs

arXiv: https://arxiv.org/abs/1711.05401 · HTML: https://mlsanity.com/paper/1711.05401/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2017.

## Built on by (most cited first, 2 of 2)

- [Separate-and-Aggregate: A Transformer-based Patch Refinement Model for Knowledge Graph Completion](https://mlsanity.com/paper/2307.05627/) (2023)
- [DeepE: a deep neural network for knowledge graph embedding](https://mlsanity.com/paper/2211.04620/) (2022)

## Abstract (arXiv)

We address the problem of learning vector representations for entities and relations in Knowledge Graphs (KGs) for Knowledge Base Completion (KBC). This problem has received significant attention in the past few years and multiple methods have been proposed. Most of the existing methods in the literature use a predefined characteristic scoring function for evaluating the correctness of KG triples. These scoring functions distinguish correct triples (high score) from incorrect ones (low score). However, their performance vary across different datasets. In this work, we demonstrate that a simple neural network based score function can consistently achieve near start-of-the-art performance on multiple datasets. We also quantitatively demonstrate biases in standard benchmark datasets, and highlight the need to perform evaluation spanning various datasets.