论文标题
关于积极学习的鲁棒性
On the Robustness of Active Learning
论文作者
论文摘要
主动学习关注的问题是如何确定要培训的机器学习算法的最有用的样本。正确应用时，它可能是应对人工神经网络的巨大数据要求的非常强大的工具。但是，我们发现它通常没有足够的照顾和领域知识来应用。结果，不切实际的希望是不切实际的，从一个数据集转移到另一个数据集变得不必要的困难。 在这项工作中，我们分析了不同主动学习方法相对于分类器容量，交换性和类型的鲁棒性，以及超参数和错误标记的数据。实验揭示了对用于样品选择的体系结构的可能偏见，从而导致其他分类器的次优性能。我们进一步提出了基于Simpson多样性指数的新“平方逻辑总和”方法，并研究了使用混淆矩阵在样本选择中平衡的效果。
Active Learning is concerned with the question of how to identify the most useful samples for a Machine Learning algorithm to be trained with. When applied correctly, it can be a very powerful tool to counteract the immense data requirements of Artificial Neural Networks. However, we find that it is often applied with not enough care and domain knowledge. As a consequence, unrealistic hopes are raised and transfer of the experimental results from one dataset to another becomes unnecessarily hard. In this work we analyse the robustness of different Active Learning methods with respect to classifier capacity, exchangeability and type, as well as hyperparameters and falsely labelled data. Experiments reveal possible biases towards the architecture used for sample selection, resulting in suboptimal performance for other classifiers. We further propose the new "Sum of Squared Logits" method based on the Simpson diversity index and investigate the effect of using the confusion matrix for balancing in sample selection.
