Scene Re-ranking for Recommendation
Peng Han, Shuo Shang · 2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP) · 2022
Re-ranking is to refine the candidate ranking list of recommended items, such that the re-ranked list attracts users to purchase or click more items than the candidate one without re-ranking. Items in the candidate list are often ranked by their relevance to users' interests. It is thus important to exploit the mutual influence between items in the re-ranking process. Existing re-ranking models focus on only the pairwise influence between two items, and have limited capability to exploit the local mutual influence in a group of items. Users often show successive interests on a group of relevant items, e.g., mobile phone, phone covers, wireless headset, namely scene. We propose a novel re-ranking model that jointly exploits the local mutual influence in scenes and the global mutual influence between different scenes. Scene representations are learned by graph neural network and multi-head attention. In addition, matrix factorization is utilized to learn the interactive relationship between users and scenes. The final re-ranking list is generated by sorting the predicted scores of all scenes. The results on different datasets show that our method outperforms all other state-of-the-art algorithms significantly.