arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.00363cs.LG
收藏

用于事件表示学习的半监督图注意网络

Semi-Supervised Graph Attention Networks for Event Representation Learning

Institute of Mathematics;Computer Sciences (ICMC) University of S\ ao Paulo (USP) S\ ao Carlos, Brazil joao\ pedro\;Computer Sciences (ICMC) University of S\ ao Paulo (USP) S\ ao Carlos, Brazil

Joao Pedro Rodrigues Mattos, Ricardo M. Marcacini

摘要:

新闻和社交网络的事件分析对于广泛的社会研究和现实世界的应用非常有用。最近,已经探索了事件图来对事件数据集及其复杂关系进行建模,其中事件是连接到表示位置、人名、日期和各种其他事件元数据的其他顶点的顶点。图的表示学习方法是有前途的提取潜在的功能,从事件图,使不同的分类算法的使用。然而,现有的方法无法满足事件图的基本要求,例如(i)处理半监督图嵌入以利用一些标记事件,(ii)自动确定事件顶点及其元数据顶点之间的关系的重要性,以及(iii)处理图的异构性。本文提出了一种结合图注意力网络和图正则化的GNEE(GAT神经事件嵌入)方法。首先,提出了一种事件图正则化方法,以确保图的所有顶点都接收事件特征,从而缓解图的异构性缺陷。其次,基于自注意机制的半监督图嵌入在表示学习过程中考虑已有的标记事件,并学习事件图中关系的重要性。五个真实世界的事件图和六个图嵌入方法的实验结果的统计分析表明,我们的GNEE优于最先进的半监督图嵌入方法。

英文摘要:

Event analysis from news and social networks is very useful for a wide range of social studies and real-world applications. Recently, event graphs have been explored to model event datasets and their complex relationships, where events are vertices connected to other vertices representing locations, people's names, dates, and various other event metadata. Graph representation learning methods are promising for extracting latent features from event graphs to enable the use of different classification algorithms. However, existing methods fail to meet essential requirements for event graphs, such as (i) dealing with semi-supervised graph embedding to take advantage of some labeled events, (ii) automatically determining the importance of the relationships between event vertices and their metadata vertices, as well as (iii) dealing with the graph heterogeneity. This paper presents GNEE (GAT Neural Event Embeddings), a method that combines Graph Attention Networks and Graph Regularization. First, an event graph regularization is proposed to ensure that all graph vertices receive event features, thereby mitigating the graph heterogeneity drawback. Second, semi-supervised graph embedding with self-attention mechanism considers existing labeled events, as well as learns the importance of relationships in the event graph during the representation learning process. A statistical analysis of experimental results with five real-world event graphs and six graph embedding methods shows that our GNEE outperforms state-of-the-art semi-supervised graph embedding methods.

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。

↑