Expanding Relationship for Cross Domain Recommendation

Cross-domain recommendation technique is a promising way to alleviate data sparsity issues by transferring knowledge from an auxiliary domain to a target domain. However, most existing works focus on utilizing the same users among different domains, while ignoring domain-specific users which forms the majority in real-world circumstances. In this paper, we propose a novel cross-domain learning approach--Relation Expansion based Cross-Domain Recommendation (ReCDR) to improve recommendation accuracies on small-overlapped domains. ReCDR first models the interactions in each domain as a local graph. It then forms a shared network by expanding out relationships using pre-trained node similarities. On the enhanced graph, ReCDR adopts a hierarchical attention mechanism. The output embedding will finally be combined with the local feature to balance the result for dual-target task. The proposed model is thoroughly evaluated on three real-world datasets. Experiments demonstrate superior performance compared to state-of-the-art methods.