A Meta-Learning Approach to One-Step Active Learning
This work addresses the challenge of reducing labeling costs for machine learning practitioners, presenting an incremental improvement by learning strategies rather than relying on heuristics.
The paper tackles the problem of costly label acquisition in machine learning by proposing a meta-learning approach to learn active-learning strategies in a single-shot, pool-based setting, showing encouraging experimental results.
We consider the problem of learning when obtaining the training labels is costly, which is usually tackled in the literature using active-learning techniques. These approaches provide strategies to choose the examples to label before or during training. These strategies are usually based on heuristics or even theoretical measures, but are not learned as they are directly used during training. We design a model which aims at \textit{learning active-learning strategies} using a meta-learning setting. More specifically, we consider a pool-based setting, where the system observes all the examples of the dataset of a problem and has to choose the subset of examples to label in a single shot. Experiments show encouraging results.