Sampling Subgraph Network With Application to Graph Classification

doi:10.1109/TNSE.2021.3115104

Sampling Subgraph Network With Application to Graph Classification

2021-10-01

10

OA

AI

DOI：10.1109/TNSE.2021.3115104

Original

Original request for help

Save

Abstract

En 中文

Graphs are naturally used to describe the structures of various real-world systems in biology, society, computer science etc., where subgraphs or motifs as basic blocks play an important role in function expression and information processing. However, existing research focuses on the basic statistics of certain motifs, largely ignoring the connection patterns among them. Recently, a subgraph network (SGN) model is proposed to study the potential structure among motifs, and it was found that the integration of SGN can enhance a series of graph classification methods. However, SGN model lacks diversity and is of quite high time complexity, making it difficult to widely apply in practice. In this paper, we introduce sampling strategies into SGN, and design a novel sampling subgraph network model, which is scale-controllable and of higher diversity. We also present a structural feature fusion framework to integrate the structural features of diverse sampling SGNs, so as to improve the performance of graph classification. Extensive experiments demonstrate that, by comparing with the SGN model, our new model indeed has much lower time complexity (reduced by two orders of magnitude) and can enhance a series of graph classification methods.

Keywords:

Feature extraction

Classification algorithms

Social networking (online)

Brain modeling

network sampling

subgraph network

feature fusion

graph classification

biological network

social network

Sampling Subgraph Network With Application to Graph Classification

Abstract

Journal

Organization