Robust Subgraph Learning by Monitoring Early Training Representations

TL;DR

This paper introduces SHERD, a novel method that enhances GNN robustness against adversarial attacks by detecting and removing vulnerable nodes during early training, improving classification accuracy and computational efficiency.

Contribution

SHERD leverages early training representations in GCNs to identify and remove susceptible nodes, providing a new approach for robust graph learning under adversarial conditions.

Findings

SHERD improves robustness against adversarial attacks across multiple datasets.

SHERD outperforms baseline methods in node classification accuracy.

SHERD maintains computational efficiency while enhancing robustness.

Abstract

Graph neural networks (GNNs) have attracted significant attention for their outstanding performance in graph learning and node classification tasks. However, their vulnerability to adversarial attacks, particularly through susceptible nodes, poses a challenge in decision-making. The need for robust graph summarization is evident in adversarial challenges resulting from the propagation of attacks throughout the entire graph. In this paper, we address both performance and adversarial robustness in graph input by introducing the novel technique SHERD (Subgraph Learning Hale through Early Training Representation Distances). SHERD leverages information from layers of a partially trained graph convolutional network (GCN) to detect susceptible nodes during adversarial attacks using standard distance metrics. The method identifies "vulnerable (bad)" nodes and removes such nodes to form a robust subgraph while maintaining node classification performance. Through our experiments, we demonstrate the increased performance of SHERD in enhancing robustness by comparing the network's performance on original and subgraph inputs against various baselines alongside existing adversarial attacks. Our experiments across multiple datasets, including citation datasets such as Cora, Citeseer, and Pubmed, as well as microanatomical tissue structures of cell graphs in the placenta, highlight that SHERD not only achieves substantial improvement in robust performance but also outperforms several baselines in terms of node classification accuracy and computational complexity.