Zehong-Wang/GFT
GFT: Graph Foundation Model with Transferable Tree Vocabulary, NeurIPS 2024.
This project offers a unified approach to analyze complex graph-structured data across various domains. It takes different types of graphs (like social networks, chemical structures, or citation networks) as input and provides insights by classifying nodes, edges, or entire graphs based on learned patterns. Scientists, data analysts, or researchers dealing with interconnected data can use this to adapt a single model for multiple analytical tasks.
No commits in the last 6 months.
Use this if you need to perform multiple analysis tasks (like classifying individual items, connections, or whole networks) on different types of graph data and want to use a single, adaptable model instead of separate ones.
Not ideal if your data is not structured as a graph or if you only have a single, very specific analysis task that a simpler model could handle.
Stars
59
Forks
10
Language
Python
License
MIT
Category
Last pushed
May 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Zehong-Wang/GFT"
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.