<ul><li>This study proposes a pre-trained Graph Neural Network (GNN) model on molecules without human annotations or prior knowledge.</li><li>The previous pre-training methods rely on functional groups, but this approach aims to capture graph-level distinctions.</li><li>The proposed method, called Subgraph-conditioned Graph Information Bottleneck (S-CGIB), generates well-distinguished graph-level representations and discovers functional groups.</li><li>Experiments show the superiority of the S-CGIB approach on molecule datasets across different domains.</li></ul>

Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck

Discover more