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 2406.08428cs.LGcs.AI
收藏

通过抽象提升噪声鲁棒性及其对机器学习的影响

Improving Noise Robustness through Abstractions and its Impact on Machine Learning

Sano - Centre for Computational Personalised Medicine(Sano个性化计算医学中心)

Alfredo Ibias, Karol Capala, Varun Ravi Varma, Anna Drozdz, Jose Sousa

AI总结:

本文提出利用数据抽象带来的信息损失减轻噪声影响,并在数值数据二分类任务中比较原始与抽象数据训练的神经网络,证明抽象可提升噪声鲁棒性。

摘要:

噪声是学习理论中的一个基本问题,并且由于现实世界数据往往带有噪声,它会对机器学习(ML)方法的应用产生巨大影响。此外,恶意噪声的引入可能导致机器学习方法严重失效,对抗性攻击就是这种情况。因此,寻找并开发能够提升噪声鲁棒性的替代方案,是机器学习中的一个基础性问题。本文提出一种处理噪声的方法:通过使用数据抽象来减轻噪声的影响。其目标是借助抽象所产生的信息损失,降低噪声对模型性能的影响。然而,这种信息损失也伴随着代价:由于信息缺失,它可能导致准确率下降。首先,针对数值数据和二分类任务这一特定情形,我们利用训练数据集探索了多种创建抽象的方法。我们还通过若干实验测试了这些抽象如何影响噪声鲁棒性,这些实验比较了人工神经网络在使用原始数据训练与使用抽象数据训练时对噪声的鲁棒性。结果清楚表明,使用抽象是开发具有噪声鲁棒性的机器学习方法的一种可行途径。

英文摘要:

Noise is a fundamental problem in learning theory with huge effects in the application of Machine Learning (ML) methods, due to real world data tendency to be noisy. Additionally, introduction of malicious noise can make ML methods fail critically, as is the case with adversarial attacks. Thus, finding and developing alternatives to improve robustness to noise is a fundamental problem in ML. In this paper, we propose a method to deal with noise: mitigating its effect through the use of data abstractions. The goal is to reduce the effect of noise over the model's performance through the loss of information produced by the abstraction. However, this information loss comes with a cost: it can result in an accuracy reduction due to the missing information. First, we explored multiple methodologies to create abstractions, using the training dataset, for the specific case of numerical data and binary classification tasks. We also tested how these abstractions can affect robustness to noise with several experiments that explore the robustness of an Artificial Neural Network to noise when trained using raw data \emph{vs} when trained using abstracted data. The results clearly show that using abstractions is a viable approach for developing noise robust ML methods.

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。

↑