GADD: Game-Inspired Adversarial Distillation for Robust Graph Defense
Graph neural networks (GNNs) are highly effective on relational data, yet their performance degrades sharply when graph topology is poisoned before training. Existing defenses usually assume a fixed attack pattern and a fixed graph structure, which makes them brittle when the poisoned graph changes...
Збережено в:
| Автори: | , , , , , |
|---|---|
| Формат: | Artigo |
| Мова: | Inglês |
| Опубліковано: |
MDPI AG
2026-05-01
|
| Серія: | Information |
| Предмети: | |
| Онлайн доступ: | https://www.mdpi.com/2078-2489/17/6/527 |
| Теги: |
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|