Talos: A More Effective and Efficient Adversarial Defense for GNN Models Based on the Global Homophily of Graphs

Documenti analoghi

• Perseus: Leveraging Common Data Patterns with Curriculum Learning for More Robust Graph Neural Networks
  di: Xia, Kaiwen, et al.
  Pubblicazione: (2024)
• ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splitting
  di: Guo, Jingwei, et al.
  Pubblicazione: (2022)
• Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses
  di: Wang, Yongyu
  Pubblicazione: (2025)
• Universal Graph Backdoor Defense: A Feature-based Homophily Perspective
  di: Pan, Mengting, et al.
  Pubblicazione: (2026)
• HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training
  di: Xu, Wen, et al.
  Pubblicazione: (2026)