Dynamical Graph Echo State Networks with Snapshot Merging for Dissemination Process Classification

TL;DR

This paper introduces a novel approach combining snapshot merging with Dynamical Graph Echo State Networks to improve classification of dissemination processes in temporal graphs, achieving better results than existing models.

Contribution

The study proposes a new data augmentation strategy called snapshot merging integrated with DynGESN for enhanced temporal graph classification.

Findings

Outperforms DynGESN and kernel-based models on benchmark datasets.

Improves classification accuracy for dissemination process patterns.

Demonstrates effectiveness of snapshot merging in temporal graph analysis.

Abstract

The Dissemination Process Classification (DPC) is a popular application of temporal graph classification. The aim of DPC is to classify different spreading patterns of information or pestilence within a community represented by discrete-time temporal graphs. Recently, a reservoir computing-based model named Dynamical Graph Echo State Network (DynGESN) has been proposed for processing temporal graphs with relatively high effectiveness and low computational costs. In this study, we propose a novel model which combines a novel data augmentation strategy called snapshot merging with the DynGESN for dealing with DPC tasks. In our model, the snapshot merging strategy is designed for forming new snapshots by merging neighboring snapshots over time, and then multiple reservoir encoders are set for capturing spatiotemporal features from merged snapshots. After those, the logistic regression is adopted for decoding the sum-pooled embeddings into the classification results. Experimental results on six benchmark DPC datasets show that our proposed model has better classification performances than the DynGESN and several kernel-based models.