论文标题
预算上的积极学习：相反的策略适合高预算
Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
论文作者
论文摘要
研究积极的学习，我们专注于标记的示例数量（预算规模）和合适的查询策略之间的关系。我们的理论分析表明，一种让人联想到相变的行为：预算低时最好查询典型的示例，而预算较大时最好查询非代表性的示例。合并的证据表明，类似现象发生在共同的分类模型中。因此，我们提出了典型lust，这是一种适合低预算的深度积极学习策略。在对监督学习的比较实证研究中，使用各种架构和图像数据集，Typiclust在低预算制度中的表现优于所有其他活跃的学习策略。在半监督框架中使用TypicLust，性能得到了更加显着的提升。特别是，在CIFAR-10上训练的最新半监督方法，其标记为10个标记的示例，达到93.2％的精度 - 比随机选择提高了39.4％。代码可在https://github.com/avihu111/typiclust上找到。
Investigating active learning, we focus on the relation between the number of labeled examples (budget size), and suitable querying strategies. Our theoretical analysis shows a behavior reminiscent of phase transition: typical examples are best queried when the budget is low, while unrepresentative examples are best queried when the budget is large. Combined evidence shows that a similar phenomenon occurs in common classification models. Accordingly, we propose TypiClust -- a deep active learning strategy suited for low budgets. In a comparative empirical investigation of supervised learning, using a variety of architectures and image datasets, TypiClust outperforms all other active learning strategies in the low-budget regime. Using TypiClust in the semi-supervised framework, performance gets an even more significant boost. In particular, state-of-the-art semi-supervised methods trained on CIFAR-10 with 10 labeled examples selected by TypiClust, reach 93.2% accuracy -- an improvement of 39.4% over random selection. Code is available at https://github.com/avihu111/TypiClust.
