.png){kind=icon}
.png){kind=icon}
Return
Feature norm-based regularization for robust out-of-distribution detection in graph neural networks
.png){kind=icon}
PRE
AI
J
DOI：10.1016/j.neucom.2026.134743.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We introduce feature norm regularization to enhance GNN robustness against OOD samples without altering the architecture or adding data. • We identify norm anomalies as key signals for OOD detection, improving GNN reliability in safety-critical domains. • We demonstrate through experiments that our method boosts detection accuracy and model stability across various benchmarks.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available
Cited Papers