核心概念
GNNs for link prediction exhibit miscalibration, requiring calibration methods like IN-N-OUT to improve accuracy.
統計資料
GNNs are often miscalibrated in link prediction tasks.
IN-N-OUT consistently outperforms baselines in calibration experiments.
引述
"IN-N-OUT significantly improves the calibration of GNNs in link prediction."
"GNNs are often overconfident in positive predictions and underconfident in negative ones."