As shown in Figure 6, node-viewGTransformer contains nodedyMPN, which maintains hidden states of nodeshv,v V and performs the message passing over nodes.

Nevertheless, two issues impede the usage of GNNs in real scenarios: (1)insufficient labeled molecules forsupervised training; (2)poorgeneralization capability to new-synthesized molecules.

Single-cell RNA sequencing (scRNA-seq) technologies enable the exploration of cellular heterogeneity and facilitate the construction of cell atlases. However, scRNA-seq data often contain a large portion of missing values (false zeros) or noisy values, hindering downstream analyses. To recover these false zeros, propagation-based imputation methods havebeen proposed usingk-NN graphs.

Akeyrequirement forthe success ofsupervised deep learning isalargelabeled dataset - a condition that is difficult to meet in medical image analysis.