To solve the problem of data sparsity and cold start, the cross-domain recommendation is a promising research direction in the recommender system. The goal of cross-domain recommendation is to transfer learned knowledge from the source domain to the target domain by different means to improve the performance of the recommendation. To the best of our knowledge, it is the first attempt to combine the sliced wasserstein distance and canonical correlation analysis for the cross-domain recommendation scenario. We propose a joint learning cross-domain recommendation model that can extract domain-specific and common features simultaneously, and only use the implicit feedback data of users without additional auxiliary information. Our one intuition is to reduce the reconstruction error caused by the variational inference based autoencoder model by the optimal transportation theory. Another attempt is to improve the correlation between domains by combining the idea of the canonical correlation analysis.
|
In this paper, we propose an end-to-end cross-domain recommendation model called SWCCA on the basis of the shared user scenario. The model only uses the implicit feedback of users in different domains and utilizes sliced wasserstein autoencoder as the main architecture to learn the latent features. We also studied how to take the correlation of hidden variables into account. We designed rigorous experiments to verify the validity of the proposed method and the results show that our method can improve recommendation effects remarkably.
注：多模态大数据智能计算实验室2019级计算机应用技术研究生赵紫安同学作为第一作者完成的论文“Sliced Wasserstein Based Canonical Correlation Analysis for Cross Domain Recommendation”在期刊Pattern Recognition Letters发表。
点击下载Sliced Wasserstein based Canonical Correlation Analysis for Cross-Domain Recommendation.pdf
