Qiangsheng Feng

E-RNS : Enhancing Negative Sample Quality from Gradient Perspective for Graph Recommendation

Bayesian Personalized Ranking (BPR) is a widely used optimization function in GNN-based recommender systems, and negative samples are usually obtained through the Random Negative Sampling (RNS) method during BPR training. However, from the gradient perspective, RNS tends to select low-quality sample…