DARec: Deep Domain Adaptation for Cross-Domain Recommendation via Transferring Rating Patterns
This addresses the problem of improving recommendation accuracy across domains for users and systems, but it is incremental as it builds on existing domain adaptation concepts.
The paper tackled cross-domain recommendation by proposing DARec, a deep domain adaptation model that transfers rating patterns without auxiliary content, achieving state-of-the-art performance on public datasets.
Cross-domain recommendation has long been one of the major topics in recommender systems. Recently, various deep models have been proposed to transfer the learned knowledge across domains, but most of them focus on extracting abstract transferable features from auxilliary contents, e.g., images and review texts, and the patterns in the rating matrix itself is rarely touched. In this work, inspired by the concept of domain adaptation, we proposed a deep domain adaptation model (DARec) that is capable of extracting and transferring patterns from rating matrices {\em only} without relying on any auxillary information. We empirically demonstrate on public datasets that our method achieves the best performance among several state-of-the-art alternative cross-domain recommendation models.