Supplement to Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding 1 Additional Algorithm Details 1.1 Details of the Transformation Function

The support nodes are either positive or negative. For the transformation function, we stack multiple computation blocks as shown in Figure 1. The stacking mechanism helps the function capture comprehensive relationships between nodes such that the performance is boosted. In each computation block, there are mainly two modules. The detailed architecture of the self-attention module is illustrated in Figure 1.