cptq/SignNet-BasisNet
SignNet and BasisNet
This project offers neural network architectures, SignNet and BasisNet, designed to learn representations of graphs while being robust to how the graph's structure is oriented or represented. It takes in graph data, such as chemical molecules, and outputs predictions for graph-level properties like molecular energy or other attributes. Researchers and practitioners working with graph data in fields like chemistry or material science would find this useful for predicting properties based on structural information.
102 stars. No commits in the last 6 months.
Use this if you need to perform accurate predictions on graph data and want a neural network model that is inherently robust to arbitrary sign choices in graph eigenvectors or basis changes.
Not ideal if your primary goal is not graph-level prediction or if you are looking for ready-to-use solutions for intrinsic neural fields experiments, as those codes are not publicly available.
Stars
102
Forks
13
Language
Python
License
MIT
Category
Last pushed
Jul 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cptq/SignNet-BasisNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.