1
Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction
通过组合层次图的多粒度自监督预训练，MolCHG将键信息作为独立语义层，突破传统分子属性预测的单粒度局限。
arXiv:2605.16088v1 Announce Type: cross Abstract: Self-supervised pretraining on molecular graphs has emerged as a promising approach for molecular pr…