An efficient manifold density estimator for all recommendation systems

TL;DR

This paper introduces EMDE, a novel density estimation framework on manifolds that improves recommendation systems by efficiently handling multi-modal data and interaction types, achieving state-of-the-art results.

Contribution

EMDE provides a fixed-size, additive, and neural network-compatible density estimator for recommendation systems, unifying multi-modal and multi-interaction data handling.

Findings

Achieved state-of-the-art results on multiple recommendation datasets.

Effectively models multi-modal and multi-interaction data.

Improved recommendation accuracy in top-k and session-based tasks.

Abstract

Many unsupervised representation learning methods belong to the class of similarity learning models. While various modality-specific approaches exist for different types of data, a core property of many methods is that representations of similar inputs are close under some similarity function. We propose EMDE (Efficient Manifold Density Estimator) - a framework utilizing arbitrary vector representations with the property of local similarity to succinctly represent smooth probability densities on Riemannian manifolds. Our approximate representation has the desirable properties of being fixed-size and having simple additive compositionality, thus being especially amenable to treatment with neural networks - both as input and output format, producing efficient conditional estimators. We generalize and reformulate the problem of multi-modal recommendations as conditional, weighted density estimation on manifolds. Our approach allows for trivial inclusion of multiple interaction types, modalities of data as well as interaction strengths for any recommendation setting. Applying EMDE to both top-k and session-based recommendation settings, we establish new state-of-the-art results on multiple open datasets in both uni-modal and multi-modal settings.