divelab/LECI
The implementation of "Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization" (NeurIPS 2023)
When performing graph-based analysis, like predicting drug properties from molecular structures or classifying social network behavior, the relationships between data points can sometimes mislead your predictions if the training data doesn't perfectly represent real-world conditions. This project helps identify the core, unchangeable relationships within your graph data, allowing for more robust predictions even when environmental factors change. It takes graph data with associated labels and environment information as input and provides a more generalizable predictive model. This is useful for researchers and data scientists working with graph data in fields like chemistry, biology, or social sciences.
No commits in the last 6 months.
Use this if you need to build predictive models on graph data that are resilient to variations in data collection environments or other 'out-of-distribution' changes.
Not ideal if your graph data is small, lacks clear environmental distinctions, or if you are not a machine learning practitioner comfortable with model training and hyperparameter tuning.
Stars
22
Forks
3
Language
Python
License
GPL-3.0
Category
Last pushed
Nov 04, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/divelab/LECI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
facebookincubator/MCGrad
MCGrad is a scalable and easy-to-use tool for multicalibration. It ensures your ML model...
dholzmueller/probmetrics
Post-hoc calibration methods and metrics for classification
gpleiss/temperature_scaling
A simple way to calibrate your neural network.
yfzhang114/Generalization-Causality
关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative...
Affirm/splinator
Splinator: probabilistic calibration with regression splines