ZhiningLiu1998/BAT

[ICML'24] BAT: 🚀 Boost Class-imbalanced Node Classification with <10 lines of Code | 从拓扑视角出发10行代码改善类别不平衡节点分类

37
/ 100
Emerging

When classifying items or entities in a network (like papers in a citation graph or users in a social network) where some categories are much rarer than others, this tool improves the accuracy of identifying those rare categories. It takes your existing network data and classification model, then enhances the data's 'connections' to make the rare classes more detectable. The output is a more accurate classification model, especially for those hard-to-find items. It's for data scientists and machine learning engineers working with graph data who need to improve performance on imbalanced classification tasks.

No commits in the last 6 months.

Use this if you are performing node classification on a graph where some classes have very few examples, and your current model struggles to identify them accurately.

Not ideal if your classification problem is not on graph data, or if your dataset is already well-balanced across all classes.

graph-classification network-analysis imbalanced-data machine-learning-engineering data-science
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

27

Forks

5

Language

Python

License

MIT

Last pushed

Nov 27, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ZhiningLiu1998/BAT"

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