Feature Importance Measure for Non-linear Learning Algorithms
This addresses the need for explainability in scientific applications using machine learning, though it appears incremental as it builds on existing feature importance concepts.
The paper tackles the problem of interpreting complex non-linear learning algorithms by proposing the Measure of Feature Importance (MFI), a general method applicable to any learning machine that can detect inconspicuous features through interactions and handle both model-based and instance-based importance.
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).