基于结构感知的多图学习方法

Multi-Graph Learning Based on Structure-Aware

多图学习是一种非常重要的学习范式.与多示例学习相比,在多图学习中包表示一个对象,包中的每一个图对应一个子对象.这种数据表示方法能够表达子对象的结构信息.但是,现有的多图学习方法不仅隐含假设包内的图满足独立同分布,而且多采用将多图学习问题转变为多示例学习问题的技术思路.这类多图学习方法容易损失图自身及图间的结构信息.针对上述问题,本文提出一种基于结构感知的多图学习方法,有效学习图自身和图间的结构信息.该方法利用图核,通过计算图之间的相似度保留图自身的结构信息,通过生成包级图表达图间的结构信息,并且设计包编码器有效学习图间的结构信息.在NCI(1)、NCI(109)和AIDB三个多图数据集上的实验结果表明,所提方法相较于现有方法在准确率、精确率、F1值和AUC上分别平均提高了5.97%、3.44%、4.48%和2.56%,在召回率上平均降低了2.12%.

Multi-graph learning is a very important learning paradigm.Compared with multi-instance learning,in multi-graph learning,a bag represents an object,and each graph in the bag corresponds to a sub-object.This data representa⁃tion method can express the structural information of sub-objects.However,existing multi-graph learning methods not only implicitly assume that the graphs in the bag satisfy independent and identical distribution,but also mostly adopt the techni⁃cal idea of transforming multi-graph learning problems into multi-instance learning problems.This type of multi-graph learning method easily loses the structural information of the graph itself and the relationships between graphs.In response to the above problems,a multi-graph learning method based on structure awareness is proposed to effectively learn the struc⁃tural information of the graph itself and the relationships between graphs.This method uses graph kernels to retain the struc⁃tural information of the graph itself by calculating the similarity between graphs,expresses the structural information be⁃tween graphs by generating bag-level graphs,and designs a bag encoder to effectively learn the structural information be⁃tween graphs.Experimental results on the NCI(1),NCI(109),and AIDB datasets show that compared with existing meth⁃ods,the proposed method improved by 5.97%,3.44%,4.48%,and 2.56%in accuracy,precision,F1 value,and AUC respec⁃tively.In terms of recall rate decreased by 2.12%.