antoinedemathelin/wann

Adversarial Weighting for Domain Adaptation in Regression

24
/ 100
Experimental

This tool helps data scientists and machine learning engineers adapt existing regression models to new, but related, datasets. If you have a model trained on one set of data (source) and want it to perform well on a slightly different, target dataset without retraining from scratch, this method adjusts the importance of your original data points. It takes your trained regression model and the new target data, outputting a re-weighted model that performs better on the target domain.

No commits in the last 6 months.

Use this if you need to quickly adapt a pre-trained regression model to a new dataset where the underlying data distribution has shifted slightly, saving significant time compared to building a new model from scratch.

Not ideal if your new dataset is dramatically different from your original training data, or if you are not working with regression tasks.

predictive-modeling machine-learning-engineering regression-analysis data-drift model-adaptation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

24

Forks

3

Language

Jupyter Notebook

License

Last pushed

Jun 01, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/antoinedemathelin/wann"

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