Review-Based Cross-Domain Recommendation via Hyperbolic Embedding and Hierarchy-Aware Domain Disentanglement

The issue of data sparsity poses a significant challenge to recommender systems. In response to this, algorithms that leverage side information such as review texts have been proposed. Furthermore, Cross-Domain Recommendation (CDR), which captures domainshareable knowledge and transfers it from a richer domain (source) to a sparser one (target), has received notable attention. Nevertheless, the majority of existing methodologies assume a Euclidean embedding space, encountering difficulties in accurately representing richer text information and managing complex interactions between users and items. This paper advocates a hyperbolic CDR approach based on review texts for modeling user-item relationships. We first emphasize that conventional distance-based domain Figure 1: The geometric properties of Euclidean (E, left) and alignment techniques may cause problems because small modifications Hyperbolic spaces (H, right). A hyperbolic space leverages in hyperbolic geometry result in magnified perturbations, the advantages of a wide space by placing nodes with high ultimately leading to the collapse of hierarchical structures. To address degrees close to the origin. However, common methods in this challenge, we propose hierarchy-aware embedding and recommender systems bring the relevant nodes closer, leading domain alignment schemes that adjust the scale to extract domainshareable to a structural collapse in the hyperbolic geometry information without disrupting structural forms.