Graph classification plays a significant role in network analysis. It also faces potential security threat like adversarial attacks. Some defense methods may sacrifice algorithm complexity for robustness like adversarial training, while others may sacrifice the clean example performance such as smoothing-based defense. Most of them are suffered from high-complexity or less transferability. To address this problem, we proposed EGC$^2$, an enhanced graph classification model with easy graph compression. EGC$^2$ captures the relationship between features of different nodes by constructing feature graphs and improving aggregate node-level representation. To achieve lower complexity defense applied to various graph classification models, EGC$^2$ utilizes a centrality-based edge importance index to compress graphs, filtering out trivial structures and even adversarial perturbations of the input graphs, thus improves its robustness. Experiments on seven benchmark datasets demonstrate that the proposed feature read-out and graph compression mechanisms enhance the robustness of various basic models, thus achieving the state-of-the-art performance of accuracy and robustness in the threat of different adversarial attacks.

中文翻译：

---

EGC2：通过简单的图压缩增强图分类

图分类在网络分析中起着重要作用。它还面临潜在的安全威胁，如对抗性攻击。一些防御方法可能会为了鲁棒性而牺牲算法复杂性，例如对抗性训练，而其他防御方法可能会牺牲干净的示例性能，例如基于平滑的防御。它们中的大多数都具有高复杂性或可移植性低的问题。为了解决这个问题，我们提出了 EGC$^2$，一种易于图压缩的增强图分类模型。EGC$^2$通过构建特征图和改进聚合节点级表示来捕获不同节点的特征之间的关系。为了实现应用于各种图分类模型的低复杂度防御，EGC$^2$利用基于中心性的边重要性指数来压缩图，过滤掉输入图的琐碎结构甚至对抗性扰动，从而提高其鲁棒性。在七个基准数据集上的实验表明，所提出的特征读出和图形压缩机制增强了各种基本模型的鲁棒性，从而在不同对抗性攻击的威胁下实现了最先进的准确性和鲁棒性性能。