Information Condensing Active Learning
arXiv:2002.07916
Abstract
We introduce Information Condensing Active Learning (ICAL), a batch mode model agnostic Active Learning (AL) method targeted at Deep Bayesian Active Learning that focuses on acquiring labels for points which have as much information as possible about the still unacquired points. ICAL uses the Hilbert Schmidt Independence Criterion (HSIC) to measure the strength of the dependency between a candidate batch of points and the unlabeled set. We develop key optimizations that allow us to scale our method to large unlabeled sets. We show significant improvements in terms of model accuracy and negative log likelihood (NLL) on several image datasets compared to state of the art batch mode AL methods for deep learning.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Equivalence of distance-based and RKHS-based statistics in hypothesis testing
- Bayesian Active Learning for Classification and Preference Learning
- EMNIST: an extension of MNIST to handwritten letters
- Deep Learning and its Application to LHC Physics
- Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
- Adversarial Active Learning for Deep Networks: a Margin Based Approach
- Demystifying MMD GANs
- Discriminative Active Learning
- Deep Active Learning over the Long Tail
- Understanding the Limitations of Variational Mutual Information Estimators
- A Kernel Test for Three-Variable Interactions
- Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent