Music Recommendations in Hyperbolic Space: An Application of Empirical Bayes and Hierarchical Poincaré Embeddings
This work addresses the problem of improving personalized playlist recommendations for users of digital music services, representing an incremental advancement by applying hyperbolic embeddings to a specific domain.
The paper tackled the problem of music recommendation by embedding a hierarchy of music entities in hyperbolic space using a novel method and parametric empirical Bayes to estimate link reliability, resulting in a large and statistically significant performance increase in A/B tests compared to Euclidean models.
Matrix Factorization (MF) is a common method for generating recommendations, where the proximity of entities like users or items in the embedded space indicates their similarity to one another. Though almost all applications implicitly use a Euclidean embedding space to represent two entity types, recent work has suggested that a hyperbolic Poincaré ball may be more well suited to representing multiple entity types, and in particular, hierarchies. We describe a novel method to embed a hierarchy of related music entities in hyperbolic space. We also describe how a parametric empirical Bayes approach can be used to estimate link reliability between entities in the hierarchy. Applying these methods together to build personalized playlists for users in a digital music service yielded a large and statistically significant increase in performance during an A/B test, as compared to the Euclidean model.