Understanding and Mitigating Under-Confidence in GNNs from the Final Layer
It is theoretically show that reducing the weight decay of the final-layer parameters alleviates GNN under-confidence by acting on the class-centroid level, while node-level calibration acts as a finer-grained complement to class-centroid-level calibration, which encourages each test node to be closer to its predicted...
Jincheng Huang, Jie Xu, Xiao-Shuang Shi et al.
· 6 citations