Mixed Supervised Graph Contrastive Learning for Recommendation

arXiv:2404.15954v1 Announce Type: cross
Abstract: Recommender systems (RecSys) play a vital role in online platforms, offering users personalized suggestions amidst vast information. Graph contrastive learning aims to learn from high-order collaborative filtering signals with unsupervised augmentation on the user-item bipartite graph, which predominantly relies on the multi-task learning framework involving both the pair-wise recommendation loss and the contrastive loss. This decoupled design can cause inconsistent optimization direction from different losses, which leads to longer convergence time and even sub-optimal performance. …

abstract arxiv augmentation collaborative collaborative filtering cs.ir cs.lg filtering framework graph information learn mixed multi-task learning online platforms personalized platforms recommendation recommender systems recsys role suggestions systems type unsupervised vast vital wise