The effectiveness of graphical recommender system depends on the quantity and quality of negative sampling. This paper selects some typical recommender system models, as well as some latest negative sampling strategies on the models as baseline. Based on typical graphical recommender model, we divide sample region into assigned-n areas and use AdaSim to give different weight to these areas to form positive set and negative set. Because of the volume and significance of negative items, we also proposed a subset selection model to narrow the core negative samples.

翻译：图推荐系统的有效性取决于负采样的数量和质量。本文选取若干典型推荐系统模型，以及这些模型上的一些最新负采样策略作为基线。基于典型图推荐模型，我们将采样区域划分为指定数量的子区域，并使用AdaSim赋予这些区域不同权重，以形成正例集和负例集。鉴于负样本的数量和重要性，我们还提出了一种子集选择模型来缩小核心负样本范围。