5975754c7650dfee0682e06e1fec0522-Supplemental-Conference.pdf

Both models consist of 2 layers and the hidden dimension is fixed to 64. We add a weight decay of 5e-4 for Cora, Citeseer, and Pubmed,and0fortherest. The optimizer configuration and the training schedule are the same as Section A.2. Kh(c ˆci) (7) where i N V denotes the evaluated node, andh is the bandwidth of the kernel function. The classwise-ECEs are summarized in Table 3, and the KDE-ECEs are collected in Table 4. Weadopt a heuristic which proportionally rescales the non top-1 output probabilities so that the calibrated probabilistic output sums up to one. While the ECEs ofCaGCN inits original paper are promising [23], we observethat the ECEs of CaGCN are often unstable and sometimes even worse than that of the uncalibrated model in our experiments.