HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration
Homophily-aware Temperature Scaling (HoTS), a simple post-hoc calibrator that assigns each node a positive scalar temperature from entropy-based logit concentration and estimated local homophily, achieves the best mean Expected Calibration Error (ECE) of 4.79%, the best average rank, and the most reliable confidence ra...
Inwoo Tae, Yoon-Jeong Hwang, Yongjae Lee
· 0 citations