reiinakano/invariant-risk-minimization

Implementation of Invariant Risk Minimization https://arxiv.org/abs/1907.02893

37
/ 100
Emerging

This project helps machine learning researchers understand and reproduce the 'Invariant Risk Minimization' technique, specifically for image classification tasks. It takes image datasets with different 'environments' (e.g., Colored MNIST) and outputs a model that ideally performs well even on new, unseen environments. This is for researchers and practitioners in machine learning focused on building robust and generalizable AI models.

No commits in the last 6 months.

Use this if you are a machine learning researcher or practitioner investigating how to build models that are less sensitive to shifts in data distributions between training and deployment environments.

Not ideal if you are looking for a plug-and-play solution for a real-world, production-ready system without deep understanding of the underlying research.

machine-learning-research domain-generalization model-robustness out-of-distribution-detection causal-inference-ml
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

92

Forks

9

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 13, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/reiinakano/invariant-risk-minimization"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.