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 based on score-based generative models. In our comprehensive evaluations with 6 benchmark datasets, our proposed SCONE significantly improves recommendation accuracy and robustness, and demonstrates the superiority of our approach over existing CF models. Furthermore, we prove the efficacy of user-item specific stochastic sampling for addressing the user sparsity and item popularity issues. The integration of the stochastic sampling and graph-based CF obtains the state-of-the-art in personalized recommendation systems, making significant strides in information-rich environments.

翻译：基于图的协同过滤（Graph-based CF）已成为推荐系统中一种有前景的方法。尽管取得了显著成就，但基于图的协同过滤模型仍面临数据稀疏性和负采样带来的挑战。本文提出了一种新颖的随机采样方法，用于：i) 对比视图（Contrastive Views）和 ii) 困难负样本（Hard Negative Samples），即SCONE方法，以克服上述问题。通过将两者均视为采样任务，我们基于基于分数的生成模型（score-based generative models），借助统一的随机采样框架生成动态增强视图和多样化的困难负样本。在6个基准数据集上的全面评估表明，本文提出的SCONE方法显著提升了推荐准确性和鲁棒性，并展示了其相较于现有协同过滤模型的优越性。此外，我们证明了针对用户-项目特定的随机采样在解决用户稀疏性和项目流行度问题上的有效性。将随机采样与基于图的协同过滤相结合，在个性化推荐系统中达到了最先进的性能，为信息丰富环境下的推荐技术带来了重要突破。