Danfoa/symmetric_learning
Torch-based library for ML problems with symmetry priors. It provides equivariant neural network modules, models, and utilities for leveraging group symmetries in data.
This library helps machine learning researchers and practitioners build more accurate and efficient models by incorporating known symmetries within their data. It takes in raw data and knowledge about its inherent symmetries, producing neural network models that inherently respect these patterns. This is ideal for those working on complex machine learning problems where data exhibits geometric or structural symmetries.
Use this if you are a machine learning researcher or developer working with data that exhibits inherent symmetries (like rotations, translations, or permutations) and you want to build more robust and data-efficient models.
Not ideal if your machine learning problem does not involve data with inherent group symmetries, as the benefits of this library would not apply.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Danfoa/symmetric_learning"
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.