Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning
This work addresses the challenge of reducing annotation costs in machine learning by automating the design of active learning algorithms, offering a novel approach that is incremental in improving generalization across heterogeneous datasets.
The paper tackles the problem of designing active learning algorithms by treating it as a meta-learning problem, using deep reinforcement learning to learn transferable query policies that generalize across diverse datasets, achieving competitive performance with existing methods.
Active learning (AL) aims to enable training high performance classifiers with low annotation cost by predicting which subset of unlabelled instances would be most beneficial to label. The importance of AL has motivated extensive research, proposing a wide variety of manually designed AL algorithms with diverse theoretical and intuitive motivations. In contrast to this body of research, we propose to treat active learning algorithm design as a meta-learning problem and learn the best criterion from data. We model an active learning algorithm as a deep neural network that inputs the base learner state and the unlabelled point set and predicts the best point to annotate next. Training this active query policy network with reinforcement learning, produces the best non-myopic policy for a given dataset. The key challenge in achieving a general solution to AL then becomes that of learner generalisation, particularly across heterogeneous datasets. We propose a multi-task dataset-embedding approach that allows dataset-agnostic active learners to be trained. Our evaluation shows that AL algorithms trained in this way can directly generalise across diverse problems.