zjukg/NeuralKG
[Tool] For Knowledge Graph Representation Learning
This project helps researchers and developers explore and evaluate different ways to represent relationships within complex datasets, often called knowledge graphs. You input a knowledge graph – a collection of interconnected facts, like "Shakespeare wrote Hamlet" – and it outputs a learned representation for each entity and relationship. This is primarily for researchers or data scientists working on knowledge graph analysis and understanding.
393 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need a flexible toolkit to experiment with various knowledge graph embedding models, including conventional, graph neural network-based, and rule-based approaches.
Not ideal if you're looking for an out-of-the-box solution to directly apply knowledge graph embeddings to a specific business problem without needing to customize or evaluate different models.
Stars
393
Forks
71
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 08, 2024
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zjukg/NeuralKG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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.