We introduce and explore a new method for inferring hidden geometric
coordinates of nodes in complex networks based on the number of common
neighbors between the nodes. We compare this approach to the HyperMap method,
which is based only on the connections (and disconnections) between
本文提出使用可学习的成对表示的神经公共邻居算法(Neural Common Neighbor, NCN)来解决关联预测任务中存在的成对关系问题。此外,为了解决网络不完整问题,也提出了两种干预方法(common neighbor completion 和 target link removal)。实验结果表明,与现有的强基线相比,该方法的表现更加优越,达到了关联预测任务中的最优水平。