XiaShan1227/Self-Attention-Graph-Pooling
Self-Attention Graph Pooling [ICML-2019]
This project helps researchers and data scientists working with complex network data, such as molecular structures or social graphs, to simplify these networks for analysis. It takes a graph dataset (like DD, MUTAG, or PROTEINS) and processes it to extract more meaningful, condensed representations. The primary users are typically those in fields like bioinformatics, cheminformatics, or network science who need to classify or understand large graphs.
No commits in the last 6 months.
Use this if you need to perform classification or other machine learning tasks on complex graph-structured data and want a method to effectively reduce the graph's size while retaining important features.
Not ideal if your data is not graph-structured or if you need a real-time, ultra-low-latency solution for massive, constantly changing graphs.
Stars
9
Forks
2
Language
Python
License
—
Category
Last pushed
Apr 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/XiaShan1227/Self-Attention-Graph-Pooling"
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.