SFR-GNN: Simple and Fast Robust GNNs against Structural Attacks

TL;DR

SFR-GNN introduces an efficient, contrastive learning-based method that enhances robustness against structural attacks in GNNs without costly purification or adaptive aggregation, significantly improving speed and accuracy.

Contribution

The paper proposes SFR-GNN, a novel, fast, and robust GNN framework that leverages mutual information theory and contrastive learning to defend against structural attacks efficiently.

Findings

Achieves 24%-162% speedup over existing robust models.

Demonstrates superior robustness in node classification tasks.

Does not require purification of modified structures.

Abstract

Graph Neural Networks (GNNs) have demonstrated commendable performance for graph-structured data. Yet, GNNs are often vulnerable to adversarial structural attacks as embedding generation relies on graph topology. Existing efforts are dedicated to purifying the maliciously modified structure or applying adaptive aggregation, thereby enhancing the robustness against adversarial structural attacks. It is inevitable for a defender to consume heavy computational costs due to lacking prior knowledge about modified structures. To this end, we propose an efficient defense method, called Simple and Fast Robust Graph Neural Network (SFR-GNN), supported by mutual information theory. The SFR-GNN first pre-trains a GNN model using node attributes and then fine-tunes it over the modified graph in the manner of contrastive learning, which is free of purifying modified structures and adaptive aggregation, thus achieving great efficiency gains. Consequently, SFR-GNN exhibits a 24%--162% speedup compared to advanced robust models, demonstrating superior robustness for node classification tasks.