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.

翻译：图神经网络（GNN）因其在图学习和节点分类任务中的卓越性能而备受关注。然而，它们对对抗攻击的脆弱性，尤其是通过易受攻击节点的攻击，给决策带来了挑战。由于攻击会在整个图中传播，因此对鲁棒图摘要的需求在对抗挑战中显而易见。在本文中，我们通过引入新技术SHERD（基于早期训练表征距离的子图学习检测）来解决图输入中的性能和对抗鲁棒性问题。SHERD利用部分训练后的图卷积网络（GCN）层的信息，通过标准距离度量检测对抗攻击期间的易受攻击节点。该方法识别“脆弱（不良）”节点，并移除这些节点以形成鲁棒子图，同时保持节点分类性能。通过实验，我们通过比较网络在原始输入和子图输入上的性能与多种基线以及现有对抗攻击，证明了SHERD在增强鲁棒性方面的性能提升。我们在多个数据集上的实验，包括引文数据集（如Cora、Citeseer和Pubmed）以及胎盘细胞图的微解剖组织结构，突显了SHERD不仅在鲁棒性能上取得了显著提升，而且在节点分类准确性和计算复杂度方面优于多种基线方法。