Deep Active Learning with Adaptive Acquisition

06/27/2019
by   Manuel Haussmann, et al.
0

Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is strictly inapplicable to active learning. Within the standardized workflow, the acquisition function is chosen among available heuristics a priori, and its success is observed only after the labeling budget is already exhausted. More importantly, none of the earlier studies report a unique consistently successful acquisition heuristic to the extent to stand out as the unique best choice. We present a method to break this vicious circle by defining the acquisition function as a learning predictor and training it by reinforcement feedback collected from each labeling round. As active learning is a scarce data regime, we bootstrap from a well-known heuristic that filters the bulk of data points on which all heuristics would agree, and learn a policy to warp the top portion of this ranking in the most beneficial way for the character of a specific data distribution. Our system consists of a Bayesian neural net, the predictor, a bootstrap acquisition function, a probabilistic state definition, and another Bayesian policy network that can effectively incorporate this input distribution. We observe on three benchmark data sets that our method always manages to either invent a new superior acquisition function or to adapt itself to the a priori unknown best performing heuristic for each specific data set.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/21/2017

Episode-Based Active Learning with Bayesian Neural Networks

We investigate different strategies for active learning with Bayesian de...
research
08/08/2017

Learning how to Active Learn: A Deep Reinforcement Learning Approach

Active learning aims to select a small subset of data for annotation suc...
research
06/19/2019

BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning

We develop BatchBALD, a tractable approximation to the mutual informatio...
research
01/10/2021

PowerEvaluationBALD: Efficient Evaluation-Oriented Deep (Bayesian) Active Learning with Stochastic Acquisition Functions

We develop BatchEvaluationBALD, a new acquisition function for deep Baye...
research
12/21/2021

Practical Active Learning with Model Selection for Small Data

Active learning is of great interest for many practical applications, es...
research
05/10/2022

ALLSH: Active Learning Guided by Local Sensitivity and Hardness

Active learning, which effectively collects informative unlabeled data f...
research
03/27/2019

Active Multi-Information Source Bayesian Quadrature

Bayesian quadrature (BQ) is a sample-efficient probabilistic numerical m...

Please sign up or login with your details

Forgot password? Click here to reset