NSLab-CUK / S-CGIBLinks
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.
☆15Updated 2 months ago
Alternatives and similar repositories for S-CGIB
Users that are interested in S-CGIB are comparing it to the libraries listed below
Sorting:
- The official codes and implementations of HimGNN model in paper:"HimGNN:a novel hierarchical molecular representations learning framewor…☆22Updated 2 years ago
- Official implementation of NeurIPS'21 paper"Motif-based Graph Self-Supervised Learning for Molecular Property Prediction"☆127Updated 2 years ago
- Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generation☆35Updated 2 years ago
- Learning to Group Auxiliary Datasets for Molecule, NeurIPS2023☆18Updated 2 years ago
- [NeurIPS 2024] Implementation of "Enhancing Graph Transformers with Hierarchical Distance Structural Encoding"☆16Updated 8 months ago
- codes for KPGT (Knowledge-guided Pre-training of Graph Transformer)☆122Updated last year
- [NeurIPS 2023] "Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules"☆40Updated last year
- [ICLR 2023] "Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules"