yifeiacc/COSTA

Code for KDD'22 paper, COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning

25
/ 100
Experimental

This project offers a specialized approach to enhance machine learning models that work with graph data, like social networks or molecular structures. It takes your existing graph features and processes them to create richer, more reliable inputs, ultimately improving the accuracy and fairness of your graph-based predictions or classifications. Data scientists and machine learning engineers working with complex graph datasets would find this useful.

No commits in the last 6 months.

Use this if you are building graph-based machine learning models and need a method to improve the quality and reduce bias in your feature augmentation process.

Not ideal if you are not working with graph data or if you need a simple, off-the-shelf data augmentation solution without delving into specific feature-space techniques.

graph-machine-learning feature-engineering data-augmentation model-training data-science
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

49

Forks

4

Language

Python

License

Last pushed

Jun 07, 2023

Commits (30d)

0

Get this data via API

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

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