In this work, we propose a novel link prediction model and further boost it by studying graph incompleteness. First, we introduce MPNN-then-SF, an innovative architecture leveraging structural feature (SF) to guide MPNN's representation pooling, with its implementation, namely Neural Common Neighbor (NCN). NCN exhibits superior expressiveness and scalability compared with existing models, which can be classified into two categories: SF-then-MPNN, augmenting MPNN's input with SF, and SF-and-MPNN, decoupling SF and MPNN. Second, we investigate the impact of graph incompleteness -- the phenomenon that some links are unobserved in the input graph -- on SF, like the common neighbor. Through dataset visualization, we observe that incompleteness reduces common neighbors and induces distribution shifts, significantly affecting model performance. To address this issue, we propose to use a link prediction model to complete the common neighbor structure. Combining this method with NCN, we propose Neural Common Neighbor with Completion (NCNC). NCN and NCNC outperform recent strong baselines by large margins, and NCNC further surpasses state-of-the-art models in standard link prediction benchmarks. Our code is available at https://github.com/GraphPKU/NeuralCommonNeighbor.

翻译：本文提出一种新型链接预测模型，并通过研究图的不完备性进一步提升了模型性能。首先，我们提出MPNN-then-SF创新架构，利用结构特征（SF）引导MPNN表示池化，其具体实现命名为神经共同邻居（NCN）。与现有两类方法（SF-then-MPNN：将SF增强至MPNN输入；SF-and-MPNN：解耦SF与MPNN）相比，NCN展现出更优的表达能力和可扩展性。其次，我们探究了图不完备性（即输入图中存在未观测链接的现象）对共同邻居等结构特征的影响。通过数据集可视化分析发现，不完备性会减少共同邻居数量并引发分布偏移，显著影响模型性能。针对该问题，我们提出利用链接预测模型补全共同邻居结构的方法，并将其与NCN结合，构建了基于补全的神经共同邻居（NCNC）。NCN与NCNC在多项指标上大幅超越近期强基线模型，NCNC更是在标准链接预测基准中全面超越当前最优模型。相关代码已开源至https://github.com/GraphPKU/NeuralCommonNeighbor。