sung-won-kim/TEG
The official source code for "Task-Equivariant Graph Few-shot Learning (TEG)" at KDD 2023.
This project helps machine learning researchers and data scientists classify new or rare types of entities in graph-structured data, even when very few examples of these new types are available. It takes existing graph data with some labeled nodes and outputs a model that can accurately predict the categories of other nodes with minimal new labeled data. This is particularly useful for those working with academic citations, e-commerce product networks, or social graphs where classes might be sparse or evolve frequently.
No commits in the last 6 months.
Use this if you need to perform node classification on graph data, especially when you encounter classes with very few labeled examples or need to classify entirely new classes quickly without extensive manual labeling.
Not ideal if you have abundant labeled data for all classes in your graph and are not concerned with classifying new or rare categories.
Stars
25
Forks
—
Language
Python
License
MIT
Category
Last pushed
Dec 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sung-won-kim/TEG"
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.