Pool-based active learning (AL) is a promising technology for increasing data-efficiency of machine learning models. However, surveys show that performance of recent AL methods is very sensitive to the choice of dataset and training setting, making them unsuitable for general application. In order to tackle this problem, the field Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting. In this work, we propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem with an Attentive Conditional Neural Process model. Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives, such as those that do not equally weight the error on all data points. We experimentally verify that our Neural Process model outperforms a variety of baselines in these settings. Finally, our experiments show that our model exhibits a tendency towards improved stability to changing datasets. However, performance is sensitive to choice of classifier and more work is necessary to reduce the performance the gap with the myopic oracle and to improve scalability. We present our work as a proof-of-concept for LAL on nonstandard objectives and hope our analysis and modelling considerations inspire future LAL work.

翻译：基于池的主动学习（AL）是提升机器学习模型数据效率的一项前景广阔的技术。然而，调研表明，近期主动学习方法的性能对数据集和训练设置的选择高度敏感，使其难以适用于通用场景。为解决此问题，学习主动学习（LAL）领域提出让主动学习策略本身进行学习，从而使其能够适应特定环境。本文提出一种用于分类任务的新型LAL方法，该方法利用注意力条件神经过程模型，挖掘主动学习问题中的对称性与独立性性质。我们的方法基于从短视先知（myopic oracle）学习，使模型能够适应非标准目标（例如，对数据点误差赋予不同权重的目标）。实验验证表明，在此类场景下，我们的神经过程模型性能优于多种基线方法。最后，实验结果显示，该模型在应对数据集变化时表现出更优的稳定性趋势。然而，其性能仍受分类器选择的敏感影响，需进一步研究以缩小与短视先知之间的性能差距并提升可扩展性。我们将此工作作为面向非标准目标的LAL概念验证，期望我们的分析与建模思考能为未来LAL研究提供启示。