benedekrozemberczki/SimGNN
A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).
This project helps scientists, chemists, or materials engineers quickly compare complex chemical compounds or molecular structures. You input pairs of graph-like data representing structures, along with their known similarity or distance. It then outputs a calculated similarity score between new, unseen pairs of structures, much faster than traditional methods.
810 stars. No commits in the last 6 months.
Use this if you need to rapidly assess the similarity or distance between many graph-structured objects, like chemical compounds, where traditional methods are too slow.
Not ideal if your data is not easily represented as graphs, or if you require absolute mathematical precision in graph edit distance calculations.
Stars
810
Forks
153
Language
Python
License
GPL-3.0
Category
Last pushed
Jan 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/benedekrozemberczki/SimGNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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.