Where are we in embedding spaces? A Comprehensive Analysis on Network Embedding Approaches for Recommender Systems

TL;DR

This paper provides a comprehensive analysis of when and how to effectively use hyperbolic embeddings in recommender systems, supported by theoretical insights and extensive empirical evaluations across various datasets and models.

Contribution

It offers a detailed analysis of the suitability of hyperbolic space for different models and datasets, introduces a new metric learning method SCML and its hyperbolic version HSCML, and demonstrates state-of-the-art performance.

Findings

Hyperbolic space is more effective for certain models and datasets.

HSCML outperforms baseline methods in recommendation tasks.

Hyperbolic embeddings achieve state-of-the-art results in experiments.

Abstract

Hyperbolic space and hyperbolic embeddings are becoming a popular research field for recommender systems. However, it is not clear under what circumstances the hyperbolic space should be considered. To fill this gap, This paper provides theoretical analysis and empirical results on when and where to use hyperbolic space and hyperbolic embeddings in recommender systems. Specifically, we answer the questions that which type of models and datasets are more suited for hyperbolic space, as well as which latent size to choose. We evaluate our answers by comparing the performance of Euclidean space and hyperbolic space on different latent space models in both general item recommendation domain and social recommendation domain, with 6 widely used datasets and different latent sizes. Additionally, we propose a new metric learning based recommendation method called SCML and its hyperbolic version HSCML. We evaluate our conclusions regarding hyperbolic space on SCML and show the state-of-the-art performance of hyperbolic space by comparing HSCML with other baseline methods.