Disentanglement based Active Learning

12/15/2019
by   Silpa V S, et al.
0

We propose Disentanglement based Active Learning (DAL), a new active learning technique based on query synthesis which leverages the concept of disentanglement. Instead of requesting labels from the human oracle, our method automatically labels majority of the datapoints, thus drastically reducing the human labelling budget in active learning. The proposed method uses Information Maximizing Generative Adversarial Nets (InfoGAN) to achieve the task where the active learner provides a feedback on the generation of InfoGAN based on which decision is taken about the datapoints to be queried. Results on two benchmark datasets demonstrate that DAL is able to achieve nearly fully supervised accuracy with fairly less labelling budget compared to existing active learning approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/10/2014

Exponentiated Gradient Exploration for Active Learning

Active learning strategies respond to the costly labelling task in a sup...
research
04/30/2015

Hierarchical Subquery Evaluation for Active Learning on a Graph

To train good supervised and semi-supervised object classifiers, it is c...
research
12/17/2021

An overview of active learning methods for insurance with fairness appreciation

This paper addresses and solves some challenges in the adoption of machi...
research
01/19/2018

Active Learning of Strict Partial Orders: A Case Study on Concept Prerequisite Relations

Strict partial order is a mathematical structure commonly seen in relati...
research
11/20/2018

Computer-Assisted Fraud Detection, From Active Learning to Reward Maximization

The automatic detection of frauds in banking transactions has been recen...
research
12/13/2020

Active Learning for Node Classification: The Additional Learning Ability from Unlabelled Nodes

Node classification on graph data is an important task on many practical...
research
03/20/2017

Active Decision Boundary Annotation with Deep Generative Models

This paper is on active learning where the goal is to reduce the data an...

Please sign up or login with your details

Forgot password? Click here to reset