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.

基于池的主动学习方法对于增加机器学习模型的数据效率具有潜力，但现有方法对数据集和训练设置选择非常敏感，因此不适用于一般应用。为了解决这个问题，学习主动学习（LAL）领域建议学习主动学习策略本身，使其能够适应特定的设置。本研究提出了一种基于关注条件神经过程模型的用于分类的新型 LAL 方法，利用主动学习问题的对称性和独立性属性。我们的方法基于从一个近视的预测模型进行学习，使得我们的模型能够适应非标准目标，如不平等权重的错误。我们的实验证明，在这些设置下，我们的神经过程模型优于多种基线方法。最后，我们的实验表明，我们的模型对于不同数据集的稳定性有所提高。然而，分类器的选择会对性能产生影响，还需要更多的工作来减小与近视预测模型的性能差距，并提高可伸缩性。我们将我们的工作作为对非标准目标的 LAL 的概念验证，并希望我们的分析和建模考虑能够为未来的 LAL 工作提供启发。