Extreme-classification/GalaXC
GalaXC: Graph Neural Networks with Labelwise Attention for Extreme Classification
This project helps with classifying text documents, like product titles or articles, into a very large number of categories. You provide the text content and pre-computed numerical representations (embeddings) of your documents and categories. It then efficiently assigns the most relevant categories to each document. This is useful for anyone managing large content libraries or product catalogs who needs to accurately tag items.
No commits in the last 6 months.
Use this if you need to categorize text documents into tens or hundreds of thousands, or even millions, of possible labels with high accuracy.
Not ideal if your classification task involves only a small number of categories, or if you don't have pre-computed numerical representations for your text and labels.
Stars
33
Forks
7
Language
Python
License
MIT
Category
Last pushed
Oct 28, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Extreme-classification/GalaXC"
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.