Semi-supervised classification on graphs using explicit diffusion dynamics

TL;DR

This paper introduces Graph Diffusion Reclassification (GDR), a novel semi-supervised classification method that leverages explicit graph diffusion dynamics to improve accuracy, and extends GCNs to incorporate directed graphs.

Contribution

It proposes a new diffusion-based reclassification technique and an extended GCN architecture that explicitly models diffusion dynamics for improved graph-based classification.

Findings

GDR achieves state-of-the-art accuracy on benchmark datasets.

Diff-GCN effectively incorporates directed graph information.

Explicit diffusion dynamics enhance feature and graph integration.

Abstract

Classification tasks based on feature vectors can be significantly improved by including within deep learning a graph that summarises pairwise relationships between the samples. Intuitively, the graph acts as a conduit to channel and bias the inference of class labels. Here, we study classification methods that consider the graph as the originator of an explicit graph diffusion. We show that appending graph diffusion to feature-based learning as an \textit{a posteriori} refinement achieves state-of-the-art classification accuracy. This method, which we call Graph Diffusion Reclassification (GDR), uses overshooting events of a diffusive graph dynamics to reclassify individual nodes. The method uses intrinsic measures of node influence, which are distinct for each node, and allows the evaluation of the relationship and importance of features and graph for classification. We also present diff-GCN, a simple extension of Graph Convolutional Neural Network (GCN) architectures that leverages explicit diffusion dynamics, and allows the natural use of directed graphs. To showcase our methods, we use benchmark datasets of documents with associated citation data.