# Feature Importance Measure for Non-linear Learning Algorithms

arXiv: https://arxiv.org/abs/1611.07567 · HTML: https://mlsanity.com/paper/1611.07567/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2016.

## Built on by (most cited first, 5 of 5)

- [This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation](https://mlsanity.com/paper/2108.12204/) (2021)
- [NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights](https://mlsanity.com/paper/2106.10185/) (2021)
- [Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science](https://mlsanity.com/paper/2303.00652/) (2023)
- [Explaining Bayesian Neural Networks](https://mlsanity.com/paper/2108.10346/) (2021)
- [DORA: Exploring Outlier Representations in Deep Neural Networks](https://mlsanity.com/paper/2206.04530/) (2022)

## Abstract (arXiv)

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).