dhw059 / DenseGNN
DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
☆13Updated last month
Alternatives and similar repositories for DenseGNN:
Users that are interested in DenseGNN are comparing it to the libraries listed below
- SLICES: An Invertible, Invariant, and String-based Crystal Representation [2023, Nature Communications] MatterGPT☆88Updated last month
- [ICLR 2024] The implementation for the paper "Space Group Constrained Crystal Generation"☆37Updated 2 months ago
- AI for crystal materials☆31Updated this week
- FTCP code☆33Updated last year
- ☆11Updated last year
- A Large Language Model of the CIF format for Crystal Structure Generation☆88Updated last month
- This is a simple but efficient implementation of PaiNN-model for constructing machine learning interatomic potentials☆16Updated 2 years ago
- An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]☆18Updated 4 months ago
- A text-guided diffusion model for crystal structure generation☆35Updated last week
- ☆28Updated 2 years ago
- Crystal Edge Graph Attention Neural Network☆19Updated 8 months ago
- Crystal graph attention neural networks for materials prediction☆27Updated last year
- Scalable graph neural networks for materials property prediction☆53Updated last year
- Official implementation of DeepDFT model☆70Updated last year
- ☆24Updated 11 months ago
- ☆25Updated 2 months ago
- Generative materials benchmarking metrics, inspired by guacamol and CDVAE.☆35Updated 8 months ago
- ☆23Updated 6 months ago
- A Reinforcement Framework for Inverse Design of MOFs☆25Updated 6 months ago
- Heat capacity predictor for porous materials☆13Updated 8 months ago
- ☆16Updated 6 months ago
- Graph neural network potential with charge transfer☆34Updated 2 years ago
- Reference implementation of "SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects"☆69Updated 2 years ago
- BAMBOO (Bytedance AI Molecular BOOster) is an AI-driven machine learning force field designed for precise and efficient electrolyte simu…☆50Updated last month
- Original implementation of CSPML☆23Updated last month
- We developed a novel method, MOF-CGCNN, to efficiently and accurately predict the methane the volumetric uptakes at 65 bar for MOFs. Two …☆16Updated 3 years ago
- ☆60Updated this week
- Source code for generating materials with 20 space groups using PGCGM☆33Updated 2 years ago
- A large scale benchmark of materials design methods: https://www.nature.com/articles/s41524-024-01259-w☆63Updated last month
- Composition-Conditioned Crystal GAN pytorch code☆43Updated 2 years ago