Pseudo-Riemannian Embedding Models for Multi-Relational Graph Representations

Saee Gopal Paliwal, Angus Brayne, Benedek Fabian, Maciej Wiatrak, Aaron Sim.

PDF

In this paper we generalize single-relation pseudo-Riemannian graph embedding models to multi-relational networks, and show that the typical approach of encoding relations as manifold transformations translates from the Riemannian to the pseudo-Riemannian case. In addition we construct a view of relations as separate spacetime submanifolds of multi-time manifolds, and consider an interpolation between a pseudo-Riemannian embedding model and its Wick-rotated Riemannian counterpart. We validate these extensions in the task of link prediction, focusing on flat Lorentzian manifolds, and demonstrate their use in both knowledge graph completion and knowledge discovery in a biological domain.

Citation

@inproceedings{
paliwal2022pseudo,
title={Pseudo-Riemannian Embedding Models for Multi-Relational Graph Representations},
author={Saee Gopal Paliwal and Angus Brayne and Benedek Fabian and Maciej Wiatrak and Aaron Sim},
booktitle={4th Conference on Automated Knowledge Base Construction},
year={2022}
}