EGC2: Enhanced Graph Classification with Easy Graph Compression
This work addresses security threats in network analyses for graph classification, offering a robust defense method with improved performance.
The paper tackled the problem of adversarial attacks on graph classification models by proposing EGC2, which uses feature graphs and centrality-based compression to filter out trivial structures and adversarial perturbations, achieving state-of-the-art accuracy and robustness on ten benchmark datasets.
Graph classification is crucial in network analyses. Networks face potential security threats, such as adversarial attacks. Some defense methods may trade off the algorithm complexity for robustness, such as adversarial training, whereas others may trade off clean example performance, such as smoothingbased defense. Most suffer from high complexity or low transferability. To address this problem, we proposed EGC2, an enhanced graph classification model with easy graph compression. EGC2 captures the relationship between the features of different nodes by constructing feature graphs and improving the aggregation of the node-level representations. To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness. Experiments on ten benchmark datasets demonstrate that the proposed feature read-out and graph compression mechanisms enhance the robustness of multiple basic models, resulting in a state-of-the-art performance in terms of accuracy and robustness against various adversarial attacks.