Discriminative Active Learning

Abstract

We propose a new batch mode active learning algorithm designed for neural networks and large query batch sizes. The method, Discriminative Active Learning (DAL), poses active learning as a binary classification task, attempting to choose examples to label in such a way as to make the labeled set and the unlabeled pool indistinguishable. Experimenting on image classification tasks, we empirically show our method to be on par with state of the art methods in medium and large query batch sizes, while being simple to implement and also extend to other domains besides classification tasks. Our experiments also show that none of the state of the art methods of today are clearly better than uncertainty sampling when the batch size is relatively large, negating some of the reported results in the recent literature.

11 pages, 3 figures

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Bayesian Active Learning with Image Data
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Adversarial Active Learning for Deep Networks: a Margin Based Approach
• A Benchmark and Comparison of Active Learning for Logistic Regression
• Generative Adversarial Active Learning
• Deep Active Learning over the Long Tail
• Active Learning for Speech Recognition: the Power of Gradients

Cited by in corpus (26)

• Fine-Tuning Language Models from Human Preferences
• A Survey of Active Learning for Text Classification using Deep Neural Networks
• Deep Active Learning for Computer Vision: Past and Future
• Deep Active Learning: Unified and Principled Method for Query and Training
• Small-Text: Active Learning for Text Classification in Python
• Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography
• Discrepancy-Based Active Learning for Domain Adaptation
• Diffusion-based Deep Active Learning
• Forgetful Active Learning with Switch Events: Efficient Sampling for Out-of-Distribution Data
• Deep Multi-Fidelity Active Learning of High-dimensional Outputs
• DEAL: Difficulty-aware Active Learning for Semantic Segmentation
• Active learning for object detection in high-resolution satellite images
• Multi-class Text Classification using BERT-based Active Learning
• Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model
• Synthetic Information towards Maximum Posterior Ratio for deep learning on Imbalanced Data
• Active Deep Learning on Entity Resolution by Risk Sampling
• Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
• Information Condensing Active Learning
• Discriminative Active Learning for Domain Adaptation
• Sampling Bias in Deep Active Classification: An Empirical Study
• Effective Version Space Reduction for Convolutional Neural Networks
• ALLWAS: Active Learning on Language models in WASserstein space
• VirAAL: Virtual Adversarial Active Learning For NLU
• Towards Interpretable and Learnable Risk Analysis for Entity Resolution
• Low-Regret Active learning
• Bias-Aware Heapified Policy for Active Learning