Feature Importance Measure for Non-linear Learning Algorithms
By Marina M.-C. Vidovic, Nico Görnitz, K. Müller, Marius Kloft. 2016
40 citations recorded by the source corpus.
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).
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Dino Pedreschi
- Fosca Giannotti
- Riccardo Guidotti
- Anna Monreale
- Franco Turini
- Salvatore Ruggieri
- Sara Hajian
- Indrė Žliobaitė
Citations in the corpus
- A Survey of Methods for Explaining Black Box Models (2018, background): “A further extension of FIRM is proposed in Reference [124].”
- Methods for interpreting and understanding deep neural networks (2017, neutral): “gene sequences have been proposed [71].”