Complementary product recommendation is to recommend products to users that can be used together. Existing product recommendation methods consider all features of product's images and texts, but do not consider the relationship between visual and textual modalities, and not all features contribute equally to the complementary relationship. Based on this situation, this paper proposed a complementary product recommendation model fusing with attention mechanism(CPRFA). The model firstly enriched its feature representation with the product's image and text information. Secondly, in order to unify heterogeneous products with multimodal information, it further converted them into image and text vector representations, and then used the attention mechanism to adaptively assign weights to different features of the product. Finally, it learned the relationship between the product and the candidate products for the recommendation of complementary products. In the experiments based on the Amazon dataset, the CPRFA model outperforms other baseline models in all indicators, which shows that it can recommend complementary products to users more accurately.

[2022-06-20] Accepted Paper /doc/2022.04.0169/v1

[2022-11-05] Printed Article /doc/2022.04.0169/v2