Generative Adversarial Active Learning

Abstract

We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our idea can work with other active learning principles. We report results from various numerical experiments to demonstrate the effectiveness the proposed approach. In some settings, the proposed algorithm outperforms traditional pool-based approaches. To the best our knowledge, this is the first active learning work using GAN.

References in corpus (3)

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Improved Training of Wasserstein GANs
• Active Learning with Distributional Estimates

Cited by in corpus (31)

• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Discriminative Active Learning
• A Survey of Active Learning for Text Classification using Deep Neural Networks
• Generative Adversarial Active Learning for Unsupervised Outlier Detection
• Learning to Make Analogies by Contrasting Abstract Relational Structure
• A critical look at the current train/test split in machine learning
• Small-GAN: Speeding Up GAN Training Using Core-sets
• A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
• Deep Active Learning for Computer Vision: Past and Future
• Progressive Data Science: Potential and Challenges
• Adversarial Representation Active Learning
• Minimax Active Learning
• Deep Active Learning: Unified and Principled Method for Query and Training
• Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography
• Active Image Synthesis for Efficient Labeling
• Temporal Output Discrepancy for Loss Estimation-based Active Learning
• Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
• Medical symptom recognition from patient text: An active learning approach for long-tailed multilabel distributions
• Uncertainty-Driven Semantic Segmentation through Human-Machine Collaborative Learning
• Active Decision Boundary Annotation with Deep Generative Models
• Active Generative Adversarial Network for Image Classification
• Active Learning Under Malicious Mislabeling and Poisoning Attacks
• Thinking Outside the Pool: Active Training Image Creation for Relative Attributes
• Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
• Distribution Aware Active Learning
• Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning
• Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space
• Prediction stability as a criterion in active learning
• HumanGAN: generative adversarial network with human-based discriminator and its evaluation in speech perception modeling
• State-Relabeling Adversarial Active Learning
• Disentanglement based Active Learning