BatsResearch/zsl-kg
Framework for zero-shot learning with knowledge graphs.
This framework helps machine learning practitioners classify new types of data they haven't seen before by leveraging existing knowledge. It takes a common sense knowledge graph and data representing new categories as input, then outputs the predicted classifications. This is ideal for machine learning researchers and data scientists working on advanced classification problems.
113 stars. No commits in the last 6 months.
Use this if you need to classify data into categories for which you have no prior training examples, by using a knowledge graph to infer relationships.
Not ideal if you have ample labeled training data for all the categories you want to classify.
Stars
113
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/BatsResearch/zsl-kg"
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.