Pre-training And Transfer Learning In Recommender System

PeterRec is the first paper in the field of recommender systems to explicitly claim the universality of user representations based on self-supervised pre-training. Conure is the first lifelong learning model for user universal representation in the field of recommender systems. CLUE combines contrastive learning to obtain better results. Alibaba’s Star model and ShopperBERT model are concurrent or future work. Transferable recommender systems based on modal information are well-suited for scenarios where user or item IDs can be shared.