Stochastic Sampling for Contrastive Views and Hard Negative Samples in Graph-based Collaborative Filtering

arXiv:2405.00287v1 Announce Type: cross
Abstract: Graph-based collaborative filtering (CF) has emerged as a promising approach in recommendation systems. Despite its achievements, graph-based CF models face challenges due to data sparsity and negative sampling. In this paper, we propose a novel Stochastic sampling for i) COntrastive views and ii) hard NEgative samples (SCONE) to overcome these issues. By considering that they are both sampling tasks, we generate dynamic augmented views and diverse hard negative samples via our unified stochastic sampling framework …

abstract arxiv challenges collaborative collaborative filtering cs.ai cs.ir cs.lg data face filtering graph graph-based negative novel paper recommendation recommendation systems samples sampling sparsity stochastic systems type