Dropout-based Active Learning for Regression

Abstract

Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive. Yet most of the existing sampling methods cannot be applied to large-scale problems, consuming too much time for data processing. In this paper, we propose a fast active learning algorithm for regression, tailored for neural network models. It is based on uncertainty estimation from stochastic dropout output of the network. Experiments on both synthetic and real-world datasets show comparable or better performance (depending on the accuracy metric) as compared to the baselines. This approach can be generalized to other deep learning architectures. It can be used to systematically improve a machine-learning model as it offers a computationally efficient way of sampling additional data.

arXiv commentReport on AIST 2018; will be published in Springer LNCS series (Analysis of Images, Social Networks and Texts - 7th International Conference, AIST 2018)

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Improving neural networks by preventing co-adaptation of feature detectors
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Deep Bayesian Active Learning with Image Data
• CLTune: A Generic Auto-Tuner for OpenCL Kernels
• A Bayesian encourages dropout

Cited by in corpus (10)

• Active, Continual Fine Tuning of Convolutional Neural Networks for Reducing Annotation Efforts
• Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning
• Crowd-Powered Photo Enhancement Featuring an Active Learning Based Local Filter
• Backdoor Attack and Defense for Deep Regression
• High-contrast "gaudy" images improve the training of deep neural network models of visual cortex
• Artificial neural networks for disease trajectory prediction in the context of sepsis
• A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features
• Robust and Active Learning for Deep Neural Network Regression
• Meta-Active Learning for Node Response Prediction in Graphs
• Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation