NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion

TL;DR

NePTuNe is a hybrid neural network model that combines deep learning expressiveness with the efficiency of tensor factorization, achieving state-of-the-art results in knowledge graph completion tasks.

Contribution

The paper introduces NePTuNe, a novel hybrid model that integrates neural networks with Tucker tensor decomposition for improved link prediction in knowledge graphs.

Findings

Achieves state-of-the-art performance on FB15K-237

Near state-of-the-art on WN18RR

Balances expressiveness and computational efficiency

Abstract

Knowledge graphs link entities through relations to provide a structured representation of real world facts. However, they are often incomplete, because they are based on only a small fraction of all plausible facts. The task of knowledge graph completion via link prediction aims to overcome this challenge by inferring missing facts represented as links between entities. Current approaches to link prediction leverage tensor factorization and/or deep learning. Factorization methods train and deploy rapidly thanks to their small number of parameters but have limited expressiveness due to their underlying linear methodology. Deep learning methods are more expressive but also computationally expensive and prone to overfitting due to their large number of trainable parameters. We propose Neural Powered Tucker Network (NePTuNe), a new hybrid link prediction model that couples the expressiveness of deep models with the speed and size of linear models. We demonstrate that NePTuNe provides state-of-the-art performance on the FB15K-237 dataset and near state-of-the-art performance on the WN18RR dataset.