They Like Comedy, Don't You? A Cluster-Based Meta-Learning for Cold-Start Recommendation

Abstract

Cold start has always been a challenging problem due to the sparse user-item interaction. Recently meta-learning models have performed outstandingly in solving this problem, which train an optimal initialization parameter by sharing the knowledge of all users. However, knowledge sharing between users with different preferences is negatively affected. In this paper, we try to share knowledge only among users with similar interests. Specifically, we first propose a user cluster method in the cold start scenario. Then, with the user's cluster information we design a conversion network to transform the global initialization parameters learned by meta learning into the cluster optimal initialization parameters. In this way, we can reduce the negative impact among users with large differences in preferences, and improve the performance of the meta-learning model. Extensive experiments on MovieLens and Yelp demonstrate that our method significantly outperforms the state of the arts in both warm up and cold-start scenarios.