eraseai/erase
[CIKM-2024] Official code for work "ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance"
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.
Stars
19
Forks
2
Language
Python
License
—
Category
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.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.