Graph Diffusion-Embedding Networks

TL;DR

The paper introduces GDEN, a new graph neural network that combines feature diffusion and embedding, improving semi-supervised learning on graph data with multiple structures.

Contribution

GDEN offers a unified model integrating feature diffusion and low-dimensional embedding, handling multiple graph structures effectively.

Findings

GDEN outperforms traditional GCN models on benchmark datasets.

The model effectively handles multiple graph structures.

Experiments demonstrate improved semi-supervised learning performance.

Abstract

We present a novel graph diffusion-embedding networks (GDEN) for graph structured data. GDEN is motivated by our closed-form formulation on regularized feature diffusion on graph. GDEN integrates both regularized feature diffusion and low-dimensional embedding simultaneously in a unified network model. Moreover, based on GDEN, we can naturally deal with structured data with multiple graph structures. Experiments on semi-supervised learning tasks on several benchmark datasets demonstrate the better performance of the proposed GDEN when comparing with the traditional GCN models.