Convolutional Complex Knowledge Graph Embeddings

TL;DR

This paper introduces ConEx, a novel complex knowledge graph embedding method that uses 2D convolution and Hermitian inner products, outperforming existing models in link prediction with fewer parameters.

Contribution

ConEx is a new approach combining 2D convolution and complex embeddings, achieving superior performance with fewer parameters than state-of-the-art models.

Findings

ConEx outperforms RotatE, QuatE, and TuckER on all benchmark datasets.

ConEx requires at least 8 times fewer parameters than competing methods.

Results are reproducible with open-source code and pre-trained models.

Abstract

In this paper, we study the problem of learning continuous vector representations of knowledge graphs for predicting missing links. We present a new approach called ConEx, which infers missing links by leveraging the composition of a 2D convolution with a Hermitian inner product of complex-valued embedding vectors. We evaluate ConEx against state-of-the-art approaches on the WN18RR, FB15K-237, KINSHIP and UMLS benchmark datasets. Our experimental results show that ConEx achieves a performance superior to that of state-of-the-art approaches such as RotatE, QuatE and TuckER on the link prediction task on all datasets while requiring at least 8 times fewer parameters. We ensure the reproducibility of our results by providing an open-source implementation which includes the training, evaluation scripts along with pre-trained models at https://github.com/conex-kge/ConEx.