Abstract

Given: (a) clean training dataset, (b) trained graph machine learning pipeline, and (c) noisy test dataset; how do we make the pipeline robust to such noise? In an attempt to answer this question, we propose a modification to the pipeline that exploits both the content addressability of a restricted Boltzmann machine and the message passing capabilities of a graph neural network. We investigate which of the hidden layers of the pipeline is best suited for our proposed modification. By establishing that a decrease in mutual information indicates an increase in prediction accuracy which is in turn driven by progressive geometric clustering of the samples belonging to the same class, we attempt to explain the behaviour exhibited by the modified pipeline. Empirical results demonstrate that our approach makes the pipeline robust to some real-world noisy scenarios in citation datasets.

Metadata

publication

Expert Systems with Applications 185, 115635, 2021

year

2021

publication date

2021/12/15

authors

Ankith Mohan, Aiichiro Nakano, Emilio Ferrara

link

https://www.sciencedirect.com/science/article/pii/S0957417421010290

resource_link

https://arxiv.org/pdf/2011.10549

journal

Expert Systems with Applications

volume

185

pages

115635

publisher

Pergamon