Complex Embeddings for Simple Link Prediction

TL;DR

This paper introduces a novel link prediction method using complex-valued embeddings that effectively model various binary relations, outperforming existing models while maintaining simplicity and scalability.

Contribution

The paper proposes a simple, scalable complex embedding approach for link prediction that handles diverse relation types more effectively than prior models.

Findings

Outperforms state-of-the-art models on standard benchmarks.

Uses Hermitian dot product for efficient computation.

Handles symmetric and antisymmetric relations effectively.

Abstract

In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to solve this problem through latent factorization. However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations. Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors. Our approach is scalable to large datasets as it remains linear in both space and time, while consistently outperforming alternative approaches on standard link prediction benchmarks.