Graph embedding using multi-layer adjacent point merging model

TL;DR

This paper introduces a novel multi-layer adjacent point merging model for graph embedding that captures subgraph patterns, improving classification robustness and outperforming existing methods.

Contribution

It proposes a new graph embedding technique that extracts subgraph patterns and includes a flexible loss function for better feature selection.

Findings

Outperforms state-of-the-art graph embedding methods

Effective in capturing subgraph patterns for classification

Demonstrates robustness across different graph classification tasks

Abstract

For graph classification tasks, many traditional kernel methods focus on measuring the similarity between graphs. These methods have achieved great success on resolving graph isomorphism problems. However, in some classification problems, the graph class depends on not only the topological similarity of the whole graph, but also constituent subgraph patterns. To this end, we propose a novel graph embedding method using a multi-layer adjacent point merging model. This embedding method allows us to extract different subgraph patterns from train-data. Then we present a flexible loss function for feature selection which enhances the robustness of our method for different classification problems. Finally, numerical evaluations demonstrate that our proposed method outperforms many state-of-the-art methods.