HousE: Knowledge Graph Embedding with Householder Parameterization

TL;DR

HousE introduces a novel knowledge graph embedding framework utilizing Householder transformations, significantly enhancing the capacity to model relation patterns and mapping properties, leading to state-of-the-art results.

Contribution

The paper presents a new KGE model called HousE that employs Householder transformations for improved relation pattern modeling and mapping property handling, extending rotation-based models to high-dimensional spaces.

Findings

Achieves state-of-the-art performance on five benchmark datasets.

Models crucial relation patterns and mapping properties simultaneously.

Generalizes existing rotation-based models to high-dimensional spaces.

Abstract

The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties. However, existing approaches can only capture some of them with insufficient modeling capacity. In this work, we propose a more powerful KGE framework named HousE, which involves a novel parameterization based on two kinds of Householder transformations: (1) Householder rotations to achieve superior capacity of modeling relation patterns; (2) Householder projections to handle sophisticated relation mapping properties. Theoretically, HousE is capable of modeling crucial relation patterns and mapping properties simultaneously. Besides, HousE is a generalization of existing rotation-based models while extending the rotations to high-dimensional spaces. Empirically, HousE achieves new state-of-the-art performance on five benchmark datasets. Our code is available at https://github.com/anrep/HousE.