Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks
Mirvakhabova, Leyla, Frolov, Evgeny, Khrulkov, Valentin, Oseledets, Ivan, Tuzhilin, Alexander
We introduce a simple autoencoder based on hyperbolic geometry for solving standard collaborative filtering problem. In contrast to many modern deep learning techniques, we build our solution using only a single hidden layer. Remarkably, even with such a minimalistic approach, we not only outperform the Euclidean counterpart but also achieve a competitive performance with respect to the current state-of-the-art. We additionally explore the effects of space curvature on the quality of hyperbolic models and propose an efficient data-driven method for estimating its optimal value.
Aug-15-2020