arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.09283cs.LG
收藏

具有期望误差减少的主动学习

Active Learning with Expected Error Reduction

University of Washington(华盛顿大学);Stanford University(斯坦福大学);Apple(苹果公司)

Stephen Mussmann, Julia Reisler, Daniel Tsai, Ehsan Mousavi, Shayne O'Brien, Moises Goldszmidt

摘要:

主动学习作为一种有效的数据汇集方法已被广泛研究。在文献中的许多方法中,期望误差减少(EER)(Roy和McCallum)已被证明是主动学习的有效方法:选择在期望中最大限度地减少未标记集合上的误差的候选样本。然而,EER要求对每个候选样本重新训练模型,因此由于这种巨大的计算成本,EER尚未广泛用于现代深度神经网络。在本文中,我们重新制定下贝叶斯主动学习的镜头EER,并得出一个计算效率的版本,可以使用任何贝叶斯参数采样方法(如arXiv:1506.02142)。然后,我们比较了我们的方法的经验性能,使用蒙特卡洛退出参数采样对最先进的方法在深度主动学习文献。实验在四个标准基准数据集和三个WILDS数据集(arXiv:2012.07421)上进行。结果表明,我们的方法优于所有其他方法,除了一个在数据移位的情况下:模型依赖,非信息理论的方法,需要一个数量级更高的计算成本(arXiv:1906.03671)。

英文摘要:

Active learning has been studied extensively as a method for efficient data collection. Among the many approaches in literature, Expected Error Reduction (EER) (Roy and McCallum) has been shown to be an effective method for active learning: select the candidate sample that, in expectation, maximally decreases the error on an unlabeled set. However, EER requires the model to be retrained for every candidate sample and thus has not been widely used for modern deep neural networks due to this large computational cost. In this paper we reformulate EER under the lens of Bayesian active learning and derive a computationally efficient version that can use any Bayesian parameter sampling method (such as arXiv:1506.02142). We then compare the empirical performance of our method using Monte Carlo dropout for parameter sampling against state of the art methods in the deep active learning literature. Experiments are performed on four standard benchmark datasets and three WILDS datasets (arXiv:2012.07421). The results indicate that our method outperforms all other methods except one in the data shift scenario: a model dependent, non-information theoretic method that requires an order of magnitude higher computational cost (arXiv:1906.03671).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑