LUMIA-Group/SubTree-Attention
Official implementation for "Tailoring Self-Attention for Graph via Rooted Subtrees" (NeurIPS2023)
This project provides an advanced method for analyzing complex network data, such as social networks or citation graphs. It takes raw graph data and outputs improved classifications for individual nodes within that graph. This is useful for researchers and data scientists working with interconnected data who need more accurate insights into the relationships and categories within their networks.
No commits in the last 6 months.
Use this if you are performing node classification on graph-structured data and find that existing methods struggle to capture both local details and broader relationships across your network.
Not ideal if your data is not structured as a graph, or if you are looking for a simple, off-the-shelf solution without needing to engage with research-level graph neural networks.
Stars
11
Forks
1
Language
Python
License
—
Category
Last pushed
Oct 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LUMIA-Group/SubTree-Attention"
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.