In this paper, we aim at providing an effective Pairwise Learning Neural Link Prediction (PLNLP) framework. The framework treats link prediction as a pairwise learning to rank problem and consists of four main components, i.e., neighborhood encoder, link predictor, negative sampler and objective function. The framework is flexible that any generic graph neural convolution or link prediction specific neural architecture could be employed as neighborhood encoder. For link predictor, we design different scoring functions, which could be selected based on different types of graphs. In negative sampler, we provide several sampling strategies, which are problem specific. As for objective function, we propose to use an effective ranking loss, which approximately maximizes the standard ranking metric AUC. We evaluate the proposed PLNLP framework on 4 link property prediction datasets of Open Graph Benchmark, including \texttt{ogbl-ddi}, \texttt{ogbl-collab}, \texttt{ogbl-ppa} and \texttt{ogbl-ciation2}. PLNLP achieves Top 1 performance on \texttt{ogbl-ddi}, and Top 2 performance on \texttt{ogbl-collab} and \texttt{ogbl-ciation2} only with basic neural architecture. The performance demonstrates the effectiveness of PLNLP.
翻译:在本文中, 我们的目标是提供有效的 Pairwise 学习神经链接( PLLP) 框架 。 框架将预测作为双向学习来排列问题, 由四个主要部分组成, 即邻居编码器、 链接预测器、 负取样器和客观功能。 框架灵活, 任何通用的图形神经卷变或链接预测特定神经结构都可以用作邻居编码器。 对于链接预测器, 我们设计不同的评分功能, 可以根据不同类型的图表选择。 在负样取样器中, 我们提供若干有问题的抽样战略。 至于客观功能, 我们提议使用有效的排名损失, 以尽量扩大标准等级 IMUC。 我们评估了拟议的 PLLP 框架, 4 将开放式图表基准的属性预测数据集( 包括\ textt{ ogbbl- ddi} 、\ textt{ ogt{ { ogbbl- popa} 和 texttrobl{ 底图结构 显示业绩 。