Skip to content

Latest commit

 

History

History
46 lines (23 loc) · 864 Bytes

README.md

File metadata and controls

46 lines (23 loc) · 864 Bytes

INFORMATION GAIN PROPAGATION: A NEW WAY TO GRAPH ACTIVE LEARNING WITH SOFT LABELS.

This repository is the official implementation of IGP.

Requirements

To install requirements:

pip install -r requirements.txt

Training

To train the model(s) in the paper:

cd the “example” data

run the python file IGP.py

Results

  1. Accuracy comparison:

  1. GCN performance comparison in different budget:

  1. Ablation study:

  1. Generalization:

  1. Interpretability: