A Comparative Study on Robust Graph Neural Networks to Structural Noises

TL;DR

This paper systematically compares various robust graph neural networks under consistent structural noise settings, providing insights into their performance and practical guidance for selection.

Contribution

It offers a comprehensive comparison of different robust GNNs with standardized noise conditions, highlighting their strengths and weaknesses.

Findings

Robust GNNs vary significantly under different noise levels.

Certain models perform better against local and community noises.

Practical recommendations for robust GNN selection are provided.

Abstract

Graph neural networks (GNNs) learn node representations by passing and aggregating messages between neighboring nodes. GNNs have been applied successfully in several application domains and achieved promising performance. However, GNNs could be vulnerable to structural noise because of the message passing mechanism where noise may be propagated through the entire graph. Although a series of robust GNNs have been proposed, they are evaluated with different structural noises, and it lacks a systematic comparison with consistent settings. In this work, we conduct a comprehensive and systematical comparative study on different types of robust GNNs under consistent structural noise settings. From the noise aspect, we design three different levels of structural noises, i.e., local, community, and global noises. From the model aspect, we select some representative models from sample-based, revision-based, and construction-based robust GNNs. Based on the empirical results, we provide some practical suggestions for robust GNNs selection.