Abstract
Modern machine learning solutions require extensive data collection where labeling remains costly. To reduce this burden, open set active learning approaches aim to select informative samples from a large pool of unlabeled data that includes irrelevant or unknown classes. In this context, we propose Sharpness Aware Minimization for Open Set Active Learning (SAMOSA) as an effective querying algorithm. Building on theoretical findings concerning the impact of data typicality on the generalization properties of traditional stochastic gradient descent (SGD) and sharpness-aware minimization (SAM), SAMOSA actively queries samples based on their typicality. SAMOSA effectively identifies atypical samples that belong to regions of the embedding manifold close to the model decision boundaries. Therefore, SAMOSA prioritizes the samples that are (i) highly informative for the targeted classes, and (ii) useful for distinguishing between targeted and unwanted classes. Extensive experiments show that SAMOSA achieves up to 3% accuracy improvement over the state of the art across several datasets, while not introducing computational overhead. The source code of our experiments is available at: this https URL
Abstract (translated)
现代机器学习解决方案需要广泛的数据收集，而数据标注的成本非常高。为了减轻这一负担，开放集主动学习方法旨在从包含不相关或未知类别的大量未标记数据池中选择具有信息性的样本。在此背景下，我们提出了一种名为Sharpness Aware Minimization for Open Set Active Learning (SAMOSA)的有效查询算法。该算法基于理论发现，这些发现在数据典型性对传统随机梯度下降(SGD)和尖锐度感知最小化(SAM)泛化属性的影响方面提供了重要见解。SAMOSA根据样本的典型性主动进行样本选择。 具体来说，SAMOSA能够识别位于嵌入流形中接近模型决策边界的非典型样本。因此，它优先选择对目标类别具有高度信息性的样本，并且这些样本对于区分目标类和未期望类同样有用。广泛的实验表明，在多个数据集上，与现有技术相比，SAMOSA可以实现高达3%的准确率改进，同时不引入计算开销。 我们的实验源代码可在此 URL 获取：[请在这里插入实际链接]
URL
https://arxiv.org/abs/2510.16757
