손지원/권용진’s paper has been accepted in

Title: DIREC: Diffusion-Based Review-Embedding Generation for Accurate Cross-Domain Recommendation
Author: Jiwon Son, Yongjin Kwon, and Sang-Wook Kim
Abstract
The goal of Cross-domain Recommender System (CDRS) is to recommend items in a target domain for users who have no targetdomain 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 targetdomain user–item pair, we propose DIREC, a conditional-diffusionbased CDRS that generates a target-domain review embedding and then predicts the corresponding rating from the generated embedding. DIREC improves review embedding generation with two key ideas: (Idea 1) target-aware source attention to construct review guidance (i.e., 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 DIREC consistently outperforms eight competitors, reducing MAE by up to 14.7%. Our code and data are available at https://anonymous.4open.science/r/DIREC-3065.