pykeen/ilpc2022
🏅 KG Inductive Link Prediction Challenge (ILPC) 2022
This project provides datasets and a framework for evaluating how well machine learning models can predict missing connections in knowledge graphs, even when dealing with entirely new entities not seen during training. It takes existing knowledge graph data (like from Wikidata) and splits it into distinct training and inference sets. The output helps machine learning researchers and practitioners benchmark and develop advanced models for inductive link prediction.
No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner working with knowledge graphs and need to test how well your models can generalize to new, unseen data and entities.
Not ideal if you are looking for a pre-trained, production-ready model for transductive link prediction where all entities are known at training time.
Stars
85
Forks
17
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pykeen/ilpc2022"
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.