VM-Rec: A Variational Mapping Approach for Cold-Start User Recommendation

The cold-start problem is a common challenge for most recommender systems. The practical application of most cold-start methods is hindered by the deficiency in auxiliary content information for users. Furthermore, most methods often require simultaneous updates to extensive parameters of recommender models, resulting in high training costs, especially in large-scale industrial scenarios. We observe that the model can generate expressive embeddings for warm users with relatively more interactions. Initially, these users were cold-start users, and after transitioning to warm users, they exhibit clustering patterns in their embeddings with consistent initial interactions. Motivated by this, we propose a Variational Mapping approach for cold-start user Recommendation (VM-Rec), mapping from few initial interactions to expressive embeddings for cold-start users. Specifically, we encode the initial interactions into a latent representation, where each dimension disentangledly signifies the degree of association with each warm user. Subsequently, we utilize this latent representation as the parameters for the mapping function, mapping (decoding) it into an expressive embedding, which can be integrated into a pre-trained recommender model directly. Our method is evaluated on three datasets, demonstrating superior performance compared to other popular cold-start methods (Code is available at https://github.com/Linan2018/VM-Rec .).