EGC2: Enhanced Graph Classification with Easy Graph Compression
Jinyin Chen, Haiyang Xiong, Haibin Zhenga, Dunjie Zhang, Jian Zhang,, Mingwei Jia, and Yi Liu

TL;DR
EGC2 introduces an enhanced graph classification approach that employs easy graph compression using centrality-based edge importance to improve robustness against adversarial attacks while maintaining high accuracy.
Contribution
The paper proposes EGC2, a novel graph classification model that combines feature graph construction with a simple compression method to enhance robustness and performance.
Findings
Improves robustness against adversarial attacks.
Achieves state-of-the-art accuracy on benchmark datasets.
Effective graph compression reduces adversarial vulnerability.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks · Complex Network Analysis Techniques · Adversarial Robustness in Machine Learning
