soda-inria/sepal
Repository for SEPAL: Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning
This project helps data scientists and machine learning engineers prepare massive, interconnected knowledge graphs for machine learning. It takes huge knowledge graphs (like those representing relationships between millions of entities) and transforms them into numerical embeddings that can be used directly in predictive models. The output is a set of feature vectors ready for tasks like classification or regression, even when dealing with extremely large and complex datasets.
Use this if you need to extract meaningful features from extremely large knowledge graphs to power downstream machine learning models.
Not ideal if your data is not a knowledge graph or if you are working with smaller datasets where scalability is not a primary concern.
Stars
24
Forks
4
Language
Python
License
BSD-3-Clause
Category
Last pushed
Nov 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/soda-inria/sepal"
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.