An Introduction to Robust Graph Convolutional Networks

TL;DR

This paper introduces a robust GCN model that incorporates autoencoders to explicitly handle errors in data, improving reliability in noisy or contaminated graph datasets.

Contribution

It proposes a novel robust GCN framework with autoencoder layers to explicitly model and mitigate data errors in single-view and multi-view graphs.

Findings

Outperforms baseline methods on real-world datasets

Demonstrates robustness against various error types

Effective in both single-view and multi-view data scenarios

Abstract

Graph convolutional neural networks (GCNs) generalize tradition convolutional neural networks (CNNs) from low-dimensional regular graphs (e.g., image) to high dimensional irregular graphs (e.g., text documents on word embeddings). Due to inevitable faulty data collection instruments, deceptive data manipulation, or other system errors, the data might be error-contaminated. Even a small amount of error such as noise can compromise the ability of GCNs and render them inadmissible to a large extent. The key challenge is how to effectively and efficiently employ GCNs in the presence of erroneous data. In this paper, we propose a novel Robust Graph Convolutional Neural Networks for possible erroneous single-view or multi-view data where data may come from multiple sources. By incorporating an extra layers via Autoencoders into traditional graph convolutional networks, we characterize and handle typical error models explicitly. Experimental results on various real-world datasets demonstrate the superiority of the proposed model over the baseline methods and its robustness against different types of error.