Active Deep Learning Guided by Efficient Gaussian Process Surrogates

01/07/2023
by   Yunpyo An, et al.
0

The success of active learning relies on the exploration of the underlying data-generating distributions, populating sparsely labeled data areas, and exploitation of the information about the task gained by the baseline (neural network) learners. In this paper, we present a new algorithm that combines these two active learning modes. Our algorithm adopts a Bayesian surrogate for the baseline learner, and it optimizes the exploration process by maximizing the gain of information caused by new labels. Further, by instantly updating the surrogate learner for each new data instance, our model can faithfully simulate and exploit the continuous learning behavior of the learner without having to actually retrain it per label. In experiments with four benchmark classification datasets, our method demonstrated significant performance gain over state-of-the-arts.

READ FULL TEXT
research
09/26/2018

Active Learning for Deep Object Detection

The great success that deep models have achieved in the past is mainly o...
research
12/02/2022

SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction

Graph neural networks have achieved significant success in representatio...
research
02/14/2022

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

We propose Active Surrogate Estimators (ASEs), a new method for label-ef...
research
09/03/2016

Graph-Based Active Learning: A New Look at Expected Error Minimization

In graph-based active learning, algorithms based on expected error minim...
research
12/12/2012

Unsupervised Active Learning in Large Domains

Active learning is a powerful approach to analyzing data effectively. We...
research
07/11/2012

Active Model Selection

Classical learning assumes the learner is given a labeled data sample, f...
research
03/02/2022

Information Gain Propagation: a new way to Graph Active Learning with Soft Labels

Graph Neural Networks (GNNs) have achieved great success in various task...

Please sign up or login with your details

Forgot password? Click here to reset