提出SAMOSA算法，高效筛选开放集主动学习中的关键样本。
SAMOSA: Sharpness Aware Minimization for Open Set Active learning
- 基于数据典型性选择样本，聚焦模型边界附近的异常点。
- 在多个数据集上比当前最优方法提升3%准确率。
- 无需额外计算开销，适合资源受限场景使用。
现代机器学习依赖大量数据，但标注成本高昂。为减轻负担，开放集主动学习旨在从包含无关或未知类别的大量未标记数据中筛选有信息量的样本。本文提出针对开放集主动学习的尖锐度感知最小化（SAMOSA）查询算法。基于传统随机梯度下降（SGD）和尖锐度感知最小化（SAM）的理论发现，SAMOSA依据样本典型性进行主动查询，有效识别嵌入流形中靠近模型决策边界的非典型样本。因此，SAMOSA优先选择对目标类别高度有用、且有助于区分目标与非目标类别的样本。大量实验表明，SAMOSA在多个数据集上相较当前最优方法提升最高达3%的准确率，且不引入额外计算开销。代码已公开于：https://anonymous.4open.science/r/samosa-DAF4。
原文摘要 · Abstract (English)
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: https://anonymous.4open.science/r/samosa-DAF4
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。