Edge-Augmented Graph Transformer

[NeurIPS'23] Source code of "Data-Centric Learning from Unlabeled Graphs with Diffusion Model": A data-centric transfer learning framework with diffusion model on graphs.

An efficient curriculum learning-based strategy for molecular graph learning

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.

Multi-View Conditional Information Bottleneck (MVCIB) is a novel architecture for pre-training Graph Neural Networks on 2D and 3D molecular structures and developed by NS Lab, CUK based on pure PyTorch backend.

CaMol is a novel architecture for predicting molecular property in few-shot scenarios and developed by NS Lab, CUK based on pure PyTorch backend.

The implementation, training and evaluation of a Structure Seer machine learning model designed for reconstruction of adjacency of a molecular graph from the labelling of its nodes.