GPRec: Bi-level User Modeling for Deep Recommenders
This work addresses the challenge of user modeling in deep recommender systems, but it appears incremental as it builds on existing methods with a bi-level approach.
The paper tackles the problem of improving recommendation quality by explicitly categorizing users into learnable groups and aligning them with group embeddings, while also refining individual preferences to be independent of group ones, resulting in significant improvements on three public datasets.
GPRec explicitly categorizes users into groups in a learnable manner and aligns them with corresponding group embeddings. We design the dual group embedding space to offer a diverse perspective on group preferences by contrasting positive and negative patterns. On the individual level, GPRec identifies personal preferences from ID-like features and refines the obtained individual representations to be independent of group ones, thereby providing a robust complement to the group-level modeling. We also present various strategies for the flexible integration of GPRec into various DRS models. Rigorous testing of GPRec on three public datasets has demonstrated significant improvements in recommendation quality.