eraseai/erase

[CIKM-2024] Official code for work "ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance"

30
/ 100
Emerging

ERASE helps machine learning practitioners improve the accuracy of deep learning models on graph-structured data, even when the initial labels for nodes in the graph are incorrect or noisy. It takes graph datasets with potentially mislabeled nodes and outputs more robust, accurate classification results. This is for data scientists and machine learning engineers working with graph data for tasks like citation network analysis or knowledge graph classification.

No commits in the last 6 months.

Use this if you are building deep learning models on graph data where obtaining perfectly clean and accurate labels for every node is difficult or expensive, and you suspect your labels might contain errors.

Not ideal if your datasets consistently have high-quality, perfectly accurate labels, or if your tasks do not involve graph-structured data.

graph-classification citation-network-analysis knowledge-graphs data-quality-improvement noisy-data-handling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

19

Forks

2

Language

Python

License

Last pushed

Aug 14, 2024

Commits (30d)

0

Get this data via API

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

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