Toward Optimal Probabilistic Active Learning Using a Bayesian Approach

06/02/2020
by   Daniel Kottke, et al.
55

Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at reducing the labeling costs by an efficient and effective allocation of costly labeling resources. In this article, we propose a decision-theoretic selection strategy that (1) directly optimizes the gain in misclassification error, and (2) uses a Bayesian approach by introducing a conjugate prior distribution to determine the class posterior to deal with uncertainties. By reformulating existing selection strategies within our proposed model, we can explain which aspects are not covered in current state-of-the-art and why this leads to the superior performance of our approach. Extensive experiments on a large variety of datasets and different kernels validate our claims.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

page 8

page 9

page 17

04/02/2021

Efficacy of Bayesian Neural Networks in Active Learning

Obtaining labeled data for machine learning tasks can be prohibitively e...
12/11/2019

Parting with Illusions about Deep Active Learning

Active learning aims to reduce the high labeling cost involved in traini...
08/17/2021

ImitAL: Learning Active Learning Strategies from Synthetic Data

One of the biggest challenges that complicates applied supervised machin...
02/16/2020

Active Bayesian Assessment for Black-Box Classifiers

Recent advances in machine learning have led to increased deployment of ...
01/31/2021

A Simple yet Brisk and Efficient Active Learning Platform for Text Classification

In this work, we propose the use of a fully managed machine learning ser...
02/28/2021

Feedback Coding for Active Learning

The iterative selection of examples for labeling in active machine learn...
09/08/2018

Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection

Deep learning for clinical applications is subject to stringent performa...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.