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 1611.07567cs.AIcs.LGstat.ML
收藏

非线性学习算法的特征重要性度量

Feature Importance Measure for Non-linear Learning Algorithms

Technical University of Berlin(柏林工业大学);Humbold University of Berlin(洪堡大学)

Marina M. -C. Vidovic, Nico Görnitz, Klaus-Robert Müller, Marius Kloft

摘要:

复杂的问题可能需要复杂的非线性学习方法,如内核机器或深度神经网络,以实现最先进的预测精度。然而,在使用机器学习解决问题时,高预测精度并不是唯一要考虑的目标。相反,特定的科学应用需要对学习的预测函数进行一些解释。不幸的是,大多数方法都没有开箱即用的直接解释。即使是线性预测函数也不能直接解释特征是否表现出复杂的相关结构。在本文中,我们提出了特征重要性度量(MFI)。MFI是通用的,可以应用于任何学习机器(包括内核机器和深度学习)。MFI本质上是非线性的,可以检测本身不明显的特征,并且仅通过与其他特征的相互作用来影响预测功能。最后,MFI可用于基于模型的特征重要性和基于实例的特征重要性(即,测量特定数据点的特征重要性)。

英文摘要:

Complex problems may require sophisticated, non-linear learning methods such as kernel machines or deep neural networks to achieve state of the art prediction accuracies. However, high prediction accuracies are not the only objective to consider when solving problems using machine learning. Instead, particular scientific applications require some explanation of the learned prediction function. Unfortunately, most methods do not come with out of the box straight forward interpretation. Even linear prediction functions are not straight forward to explain if features exhibit complex correlation structure. In this paper, we propose the Measure of Feature Importance (MFI). MFI is general and can be applied to any arbitrary learning machine (including kernel machines and deep learning). MFI is intrinsically non-linear and can detect features that by itself are inconspicuous and only impact the prediction function through their interaction with other features. Lastly, MFI can be used for both --- model-based feature importance and instance-based feature importance (i.e, measuring the importance of a feature for a particular data point).

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。

↑