学习论文 “Edge Labeling Graph Neural Network for Few shot Learning”笔记

个人笔记对模型数学上的解读部分很大程度上受到这篇博客的启发与参考 Notation T=S∪QT=S \cup QT=S∪Q,support set and query set, support set SSS in each episode serves as the labeled training set xix_ixi​ and yi∈{C1,...,CN}=CT⊂Cy_i \in \{C_1,...,C_N\}=C_T \subset Cyi​∈{C1​,...,CN​}=CT​⊂C: iii th input data and its label, CCC is the set of all