Learning Algorithms for Active Learning

2017/07/31 by Philip Bachman, Bachman, Philip, Alessandro Sordoni +3 · 3 citations
Computer Science · #Algorithms and Data Compression #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.1708.00088

openalex publication_date 2017/07/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce a model that learns active learning algorithms via metalearning. For a distribution of related tasks, our model jointly learns: a data representation, an item selection heuristic, and a method for constructing prediction functions from labeled training sets. Our model uses the item selection heuristic to gather labeled training sets from which to construct prediction functions. Using the Omniglot and MovieLens datasets, we test our model in synthetic and practical settings.

Citations

• Reinforcement and Imitation Learning via Interactive No-Regret Learning
• Bidirectional recurrent neural networks
• Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
• One-shot Learning with Memory-Augmented Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

Cited by

• On Interactive Machine Learning and the Potential of Cognitive Feedback
• How to Train Your MAML to Excel in Few-Shot Classification
• Augmented Memory Networks for Streaming-Based Active One-Shot Learning

Related

• Active Learning: Problem Settings and Recent Developments
• Learning Active Learning from Data
• MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning
• Discovering General-Purpose Active Learning Strategies
• Learning how to Active Learn: A Deep Reinforcement Learning Approach