We present a large scale hyperbolic recommender system. We discuss why hyperbolic geometry is a more suitable underlying geometry for many recommendation systems and cover the fundamental milestones and insights that we have gained from its development. In doing so, we demonstrate the viability of hyperbolic geometry for recommender systems, showing that they significantly outperform Euclidean models on datasets with the properties of complex networks. Key to the success of our approach are the novel choice of underlying hyperbolic model and the use of the Einstein midpoint to define an asymmetric recommender system in hyperbolic space. These choices allow us to scale to millions of users and hundreds of thousands of items.
@article{arxiv.1902.08648,
title = {Scalable Hyperbolic Recommender Systems},
author = {Benjamin Paul Chamberlain and Stephen R. Hardwick and David R. Wardrope and Fabon Dzogang and Fabio Daolio and Saúl Vargas},
journal= {arXiv preprint arXiv:1902.08648},
year = {2019}
}