acmi-lab/PU_learning

Code and results accompanying our paper titled Mixture Proportion Estimation and PU Learning: A Modern Approach at Neurips 2021 (Spotlight)

33
/ 100
Emerging

This project helps researchers and data scientists classify data when they only have positive examples and a mix of positive and unlabeled examples. It takes your dataset of labeled positive instances and unlabeled instances as input and outputs a model that can accurately predict new positive cases. This is for machine learning researchers and data scientists working on classification problems with incomplete label information.

No commits in the last 6 months.

Use this if you need to build a classifier but only have a small set of confirmed positive examples and a large set of data where you don't know if they are positive or negative.

Not ideal if you have a dataset with clear positive and negative labels, as standard supervised classification methods would be more appropriate.

unsupervised-learning semi-supervised-learning data-classification machine-learning-research pattern-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

46

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Mar 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/acmi-lab/PU_learning"

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