多属性事件驱动图的层次实体对齐
Hierarchical Entity Alignment for Attribute-Rich Event-Driven Graphs
摘要：
本文讨论了在属性丰富的事件驱动图中的实体对齐问题。与许多其他实体对齐问题不同，我们感兴趣的是基于它们的动作的相似性来对齐实体，即，参与类似事件的实体更有可能是相同的。我们建模的生成过程中，这个问题作为一个贝叶斯模型，并从后验预测分布推导出我们提出的算法。我们将我们的分层实体对齐（HEAT）算法应用于两个数据集，一个关于出版物，另一个关于金融交易，这些数据集来自真实数据并由外部合作者提供给我们。
英文摘要：
This paper addresses the problem of entity alignment in attribute-rich event-driven graphs. Unlike many other entity alignment problems, we are interested in aligning entities based on the similarity of their actions, i.e., entities that participate in similar events are more likely to be the same. We model the generative process of this problem as a Bayesian model and derive our proposed algorithm from the posterior predictive distribution. We apply our Hierarchical Entity AlignmenT (HEAT) algorithm to two datasets, one on publications and the other on financial transactions, derived from real data and provided to us by an external collaborator.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
