DIREC: Diffusion-Based Review-Embedding Generation for Accurate Cross-Domain Recommendation

The goal of Cross-domain Recommender System (CDRS) is to recommend items in a target domain for users who have no target-domain interactions by leveraging their source-domain interaction histories. Most existing CDRSs transfer a user embedding from the source domain to the target domain and predict ratings via embedding matching with target-domain item embeddings, which can overlook fine-grained user--item preference signals expressed in reviews. To capture such fine-grained signals for each target-domain user--item pair, we propose øurs, a conditional-diffusion-based CDRS that generates a target-domain review embedding and then predicts the corresponding rating from the generated embedding. øurs improves review-embedding generation with two key ideas: (Idea 1) target-aware source attention to construct review guidance (, a conditioning embedding); and (Idea 2) pretraining on target-domain review embeddings from target-only users to learn a broader target-domain review-embedding distribution. Extensive experiments on three cross-domain scenarios show that øurs consistently outperforms nine competitors, reducing MAE by up to 14.2%.