dmlc/GNNLens2
Visualization tool for Graph Neural Networks
This tool helps researchers and engineers understand how their Graph Neural Networks (GNNs) process information. You input your GNN model and graph data, and it generates interactive visualizations of the graph structure, node labels, edge weights, and model explanations. This is ideal for GNN developers and researchers who need to analyze, explain, and present their GNN models.
259 stars. No commits in the last 6 months.
Use this if you need to visually debug, analyze the behavior, or explain the predictions of your Graph Neural Network models built with DGL.
Not ideal if you are looking for a general-purpose graph visualization tool not specifically tailored for GNNs or if your GNN framework is not DGL.
Stars
259
Forks
29
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Sep 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dmlc/GNNLens2"
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.