Scalable Hyperbolic Recommender Systems
This addresses the challenge of improving recommendation accuracy and scalability for large-scale systems, representing a novel application of hyperbolic geometry rather than an incremental improvement.
The paper tackles the problem of recommendation systems by proposing a hyperbolic geometry-based model, showing it significantly outperforms Euclidean models on datasets with complex network properties and scales to millions of users and items.
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.