Graphlet-based lazy associative graph classification

TL;DR

This paper proposes a novel graph classification method that uses graphlet-based approximations of graph intersections to improve efficiency, demonstrated through experiments on a toxicology dataset.

Contribution

It introduces a modified lazy associative classification algorithm leveraging graphlet kernels for efficient graph intersection approximation.

Findings

Effective classification on toxicology data

Improved efficiency over traditional methods

Potential for broader applications in graph analysis

Abstract

The paper addresses the graph classification problem and introduces a modification of the lazy associative classification method to efficiently handle intersections of graphs. Graph intersections are approximated with all common subgraphs up to a fixed size similarly to what is done with graphlet kernels. We explain the idea of the algorithm with a toy example and describe our experiments with a predictive toxicology dataset.