RIM: Reliable Influence-based Active Learning on Graphs.

This repository is the official implementation of RIM.

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 RIM.py

Results

1. Accuracy comparison:

<img src="accuracy.png" width="80%" height="80%">

2. GCN performance comparison:

<img src="gcn.png" width="80%" height="80%">

3. LP performance comparison:

<img src="lp.png" width="80%" height="80%">

4. Budget performance comparison:

<img src="budget.png" width="80%" height="80%">

5. Efficiency comparison:

<img src="speedup.png" width="80%" height="80%">

6. Interpretability:

<img src="interpretbility.png" width="80%" height="80%">