Subgraph-conditioned Graph Information Bottleneck (S-CGIB) is a novel architecture for pre-training Graph Neural Networks in molecular property prediction and developed by NS Lab, CUK based on pure PyTorch backend.
graph graph-neural-networks graph-representation-learning molecular-property-prediction molecular-graph-learning graph-foundation-model pretrained-graph-model graph-information-bottleneck self-supervised-graph-learning
-
Updated
Jan 10, 2025 - Python