Graph Classification Based on Skeleton and Component Features

In these areas, data can be usually represented as graphs with labels. For example, in bioinformatics, a protein molecule can be represented as a graph whose nodes corresponds to atoms, and edges signify there exits chemical bonds or not between atoms. The graphs are allocated with different labels based on having specific function or not. To make classification in this task, we usually make a common assumption that protein molecules with similar structure have similar functional properties. More recently, there has been a surge of approaches that seek to learn representations or embeddings that encode features about the graphs and then make classification. The idea behind these learning approaches focuses on graph structure representation and learning a mapping that embeds nodes or entire (sub)graphs, into a low-dimensional vector. Most of these methods can be classified into two categories: (1) neural networks manners [4] that learn the large-scale structures of target graph, (2) kernel methods [5] that learn small-size structures of target graph. Different structures of graph imply dissimilar features. Corresponding author Email address: weiw@buaa.edu.cn