An implementation of the BADGE batch active learning algorithm. Details are provided in our article, Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds, which was presented as a talk in ICLR 2020. This code was built by modifying Kuan-Hao Huang's deep active learning repository.
To run this code fully, you'll need PyTorch (we're using version 1.4.0), scikit-learn, and OpenML. We've been running our code in Python 3.7.
python run.py --model resnet --nQuery 1000 --data CIFAR10 --alg badge
runs an active learning experiment using a ResNet and CIFAR-10 data, querying batches of 1,000 samples according to the BADGE algorithm.
This code allows you to also run each of the baseline algorithms used in our paper.
python run.py --model mlp --nQuery 10000 --did 6 --alg conf
runs an active learning experiment using an MLP and dataset number 6 from OpenML, querying batches of 10,000 with confidence sampling.
Note that in our code, OpenML datasets can only be used with MLP architectures.
See the readme file in scripts/ for more details about generating plots like those in our paper.