Core Concepts
Selbstgesteuerte Graphenstrukturverfeinerung (SG-GSR) verbessert die Robustheit von GNNs durch die Nutzung eines sauberen Teilgraphen.
Stats
Recent studies have revealed that GNNs are vulnerable to adversarial attacks.
In this paper, we propose a self-guided GSR framework (SG-GSR).
Our code is available at https://github.com/yeonjun-in/torch-SG-GSR.