arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.08541cs.LGstat.ML
收藏

图主动学习中基于区域的查询

Regional based query in graph active learning

Bar-Ilan University(巴伊兰大学)

Roy Abel, Yoram Louzoun

摘要:

图卷积网络(GCN)已经成为网络中节点分类的主要方法,并且在多个节点分类任务中达到了最高的准确率。在没有可用的标记样本的情况下,已经开发了主动学习方法,以使用对oracle的最少数量的查询来获得最高的准确度。目前最好的主动学习方法都是以样本类的不确定性作为选择准则。然而,在基于图的分类中,每个节点的类通常与其邻居的类相关。因此,节点的邻居的类别的不确定性可以是更适当的选择标准。在这里,我们提出了两个这样的标准,一个扩展的经典的不确定性措施,和其他扩展的页面排名算法。我们表明,后者是最佳的标记节点的分数时,是低的,当这个分数增长到一个超过平均程度,区域的不确定性比所有现有的方法表现更好。虽然我们已经在图上测试了这种方法,但这种方法可以扩展到任何分类问题,其中可以在输入样本之间定义距离度量。所有使用的代码都可以访问:https://github.com/louzounlab/graph-al所有使用的数据集都可以访问:https://github.com/louzounlab/DataSets

英文摘要:

Graph convolution networks (GCN) have emerged as the leading method to classify node classes in networks, and have reached the highest accuracy in multiple node classification tasks. In the absence of available tagged samples, active learning methods have been developed to obtain the highest accuracy using the minimal number of queries to an oracle. The current best active learning methods use the sample class uncertainty as selection criteria. However, in graph based classification, the class of each node is often related to the class of its neighbors. As such, the uncertainty in the class of a node's neighbor may be a more appropriate selection criterion. We here propose two such criteria, one extending the classical uncertainty measure, and the other extending the page-rank algorithm. We show that the latter is optimal when the fraction of tagged nodes is low, and when this fraction grows to one over the average degree, the regional uncertainty performs better than all existing methods. While we have tested this methods on graphs, such methods can be extended to any classification problem, where a distance metrics can be defined between the input samples. All the code used can be accessed at : https://github.com/louzounlab/graph-al All the datasets used can be accessed at : https://github.com/louzounlab/DataSets

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。

↑