Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal

TL;DR: We introduce a new batch active learning algorithm that's robust to model architecture, batch size, and dataset.

Abstract: We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of points that are disparate and high-magnitude when represented in a hallucinated gradient space, a strategy designed to incorporate both predictive uncertainty and sample diversity into every selected batch. Crucially, BADGE trades off between diversity and uncertainty without requiring any hand-tuned hyperparameters. While other approaches sometimes succeed for particular batch sizes or architectures, BADGE consistently performs as well or better, making it a useful option for real world active learning problems.

Keywords: deep learning, active learning, batch active learning

Code: [ JordanAsh/badge](https://github.com/JordanAsh/badge) + [ 3 community implementations](https://paperswithcode.com/paper/?openreview=ryghZJBKPS)

Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [MNIST](https://paperswithcode.com/dataset/mnist), [SVHN](https://paperswithcode.com/dataset/svhn)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1906.03671/code)