Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation

Abstract

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 alignment techniques may cause problems because small modifications in hyperbolic geometry result in magnified perturbations, ultimately leading to the collapse of hierarchical structures. To address this challenge, we propose hierarchy-aware embedding and domain alignment schemes that adjust the scale to extract domainshareable information without disrupting structural forms. The process involves the initial embedding of review texts in hyperbolic space, followed by feature extraction incorporating degree-based normalization and structure alignment. We conducted extensive experiments to substantiate the efficiency, robustness, and scalability of our proposed model in comparison to state-of-the-art baselines. CCS CONCEPTS• Information systems → Recommender systems.

Review-Enhanced Hierarchical Contrastive Learning for Recommendation

“…Semantic-level Methods. Semantic-level methods evaluate contextual information from reviews to capture semantic features (Choi et al 2022). Achievable technical routes focus on deep network paradigm, containing CNNs (Zheng, Noroozi, and Yu 2017;Liu et al 2019) and RNNs .…”