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 2103.14824cs.LG
收藏

自适应修正扰动水平提高模型鲁棒性

Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries

Nanjing University of Aeronautics and Astronautics(南京航空航天大学)

Kun-Peng Ning, Lue Tao, Songcan Chen, Sheng-Jun Huang

摘要:

除了高精度之外,鲁棒性对于各种应用中的机器学习模型变得越来越重要。近年来,许多研究致力于通过噪声扰动训练来提高模型的鲁棒性。现有的研究大多假设所有训练样本的扰动水平是固定的,然而这在实际任务中很难成立。事实上,过多的扰动可能会破坏一个例子的区别性内容,而不足的扰动可能无法提供有用的信息,以提高鲁棒性。出于这种观察,我们建议在训练过程中自适应地调整每个示例的扰动水平。具体而言,提出了一种新的主动学习框架,允许模型交互式地查询人类专家的正确扰动水平。通过设计一个具有成本效益的抽样策略以及一个新的查询类型,可以显着提高鲁棒性与几个查询。理论分析和实验研究均验证了该方法的有效性。

英文摘要:

In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improving the model robustness by training with noise perturbations. Most existing studies assume a fixed perturbation level for all training examples, which however hardly holds in real tasks. In fact, excessive perturbations may destroy the discriminative content of an example, while deficient perturbations may fail to provide helpful information for improving the robustness. Motivated by this observation, we propose to adaptively adjust the perturbation levels for each example in the training process. Specifically, a novel active learning framework is proposed to allow the model to interactively query the correct perturbation level from human experts. By designing a cost-effective sampling strategy along with a new query type, the robustness can be significantly improved with a few queries. Both theoretical analysis and experimental studies validate the effectiveness of the proposed approach.

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。

↑