kzkadc/regression-tta

The official implementation of "Test-time Adaptation for Regression by Subspace Alignment" (ICLR 2025).

39
/ 100
Emerging

This project helps improve the accuracy of existing prediction models when applying them to new, slightly different datasets. It takes your pre-trained regression model and unlabeled data from the new environment, then adjusts the model to perform better on this new data without needing new labels. This is ideal for machine learning engineers, data scientists, or researchers who deploy models in dynamic real-world settings.

No commits in the last 6 months.

Use this if your regression model's performance drops when deployed to a new environment with unlabeled data that differs slightly from your training data.

Not ideal if your existing model is for classification tasks, as this method is specifically designed for regression models.

predictive-modeling model-deployment domain-adaptation unsupervised-learning
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

15

Forks

4

Language

Python

License

Last pushed

Jun 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kzkadc/regression-tta"

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