On the Equivalence of Holographic and Complex Embeddings for Link Prediction

Abstract

We show the equivalence of two state-of-the-art link prediction/knowledge graph completion methods: Nickel et al's holographic embedding and Trouillon et al.'s complex embedding. We first consider a spectral version of the holographic embedding, exploiting the frequency domain in the Fourier transform for efficient computation. The analysis of the resulting method reveals that it can be viewed as an instance of the complex embedding with certain constraints cast on the initial vectors upon training. Conversely, any complex embedding can be converted to an equivalent holographic embedding.

This is a slightly modified version of the paper of the same title that appeared in ACL 2017

Cited by in corpus (12)

• Representation Learning for Dynamic Graphs: A Survey
• Knowledge Graph Completion via Complex Tensor Factorization
• Uncovering CWE-CVE-CPE Relations with Threat Knowledge Graphs
• Knowledge Representation Learning: A Quantitative Review
• Complex and Holographic Embeddings of Knowledge Graphs: A Comparison
• MDE: Multiple Distance Embeddings for Link Prediction in Knowledge Graphs
• Group Representation Theory for Knowledge Graph Embedding
• Binarized Knowledge Graph Embeddings
• Binarized Canonical Polyadic Decomposition for Knowledge Graph Completion
• Quaternion Collaborative Filtering for Recommendation
• SEEK: Segmented Embedding of Knowledge Graphs
• Knowledge Completion for Generics using Guided Tensor Factorization