Graph-based Deep-Tree Recursive Neural Network (DTRNN) for Text Classification

TL;DR

This paper introduces a novel graph-to-tree conversion mechanism and a deep-tree recursive neural network for improved text classification on graph-structured data, demonstrating superior performance on real-world datasets.

Contribution

The paper proposes the deep-tree generation algorithm and the DTRNN model, which together enhance graph-based text classification by capturing richer node representations.

Findings

DTRNN outperforms existing methods on three real-world datasets.

The deep-tree generation improves node representation accuracy.

The approach effectively captures second order proximity and homophily in graphs.

Abstract

A novel graph-to-tree conversion mechanism called the deep-tree generation (DTG) algorithm is first proposed to predict text data represented by graphs. The DTG method can generate a richer and more accurate representation for nodes (or vertices) in graphs. It adds flexibility in exploring the vertex neighborhood information to better reflect the second order proximity and homophily equivalence in a graph. Then, a Deep-Tree Recursive Neural Network (DTRNN) method is presented and used to classify vertices that contains text data in graphs. To demonstrate the effectiveness of the DTRNN method, we apply it to three real-world graph datasets and show that the DTRNN method outperforms several state-of-the-art benchmarking methods.