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％.
multi-graph learninggraph kernelstructural informationbag-structure graphindependent identical distribution
万方数据
维普
