The authors show that several methods in the literature used for explaining individual model predictions fall into the category of "additive feature attribution" methods. They proposes a new kind of additive feature attribution method based on the concept of Shapely values and call the resulting explanations the SHAP values. The authors also suggest a new kernel called the shapely kernel which can be used to compute SHAP values via linear regression (a method they call kernel SHAP). They discuss how other methods, such as DeepLIFT, can be improved by better approximating the Shapely values. Summary of review: Positives: (1) Novel and sound theoretical framework for approaching the question of model explanations, which has been very lacking in the field (most other methods were developed ad-hoc).

In the field of functional genomics, the analysis of gene expression profiles through Machine and Deep Learning is increasingly providing meaningful insight into a number of diseases. The paper proposes a novel algorithm to perform Feature Selection on genomic-scale data, which exploits the reconstruction capabilities of autoencoders and an ad-hoc defined Explainable Artificial Intelligence-based score in order to select the most informative genes for diagnosis, prognosis, and precision medicine.

Shapley values are great analytical tools in game theory to measure the importance of a player in a game. Due to their axiomatic and desirable properties such as efficiency, they have become popular for feature importance analysis in data science and machine learning. However, the time complexity to compute Shapley values based on the original formula is exponential, and as the number of features increases, this becomes infeasible. Castro et al. [1] developed a sampling algorithm, to estimate Shapley values. In this work, we propose a new sampling method based on a multilinear extension technique as applied in game theory. The aim is to provide a more efficient (sampling) method for estimating Shapley values. Our method is applicable to any machine learning model, in particular for either multi-class classifications or regression problems. We apply the method to estimate Shapley values for multilayer perceptrons (MLPs) and through experimentation on two datasets, we demonstrate that our method provides more accurate estimations of the Shapley values by reducing the variance of the sampling statistics.

Being able to explain a prediction as well as having a model that performs well are paramount in many machine learning applications. Deep neural networks have gained momentum recently on the basis of their accuracy, however these are often criticised to be black-boxes. Many authors have focused on proposing methods to explain their predictions. Among these explainability methods, feature attribution methods have been favoured for their strong theoretical foundation: the Shapley value. A limitation of Shapley value is the need to define a baseline (aka reference point) representing the missingness of a feature. In this paper, we present a method to choose a baseline based on a neutrality value: a parameter defined by decision makers at which their choices are determined by the returned value of the model being either below or above it. Based on this concept, we theoretically justify these neutral baselines and find a way to identify them for MLPs. Then, we experimentally demonstrate that for a binary classification task, using a synthetic dataset and a dataset coming from the financial domain, the proposed baselines outperform, in terms of local explanability power, standard ways of choosing them.

Previously, we looked at the pitfalls with the default "feature importance" in tree based models, talked about permutation importance, LOOC importance, and Partial Dependence Plots. Now let's switch lanes and look at a few model agnostic techniques which takes a bottom-up way of explaining predictions. Instead of looking at the model and trying to come up with global explanations like feature importance, these set of methods look at each single prediction and then try to explain them. As the name suggests, this is a model agnostic technique to generate local explanations to the model. The core idea behind the technique is quite intuitive. Suppose we have a complex classifier, with a highly non-linear decision boundary.

My iPhone screen time is over four hours every day. Over the last month I've booked restaurant reservations and doctor's appointments, received motorcycle maintenance records, loaded new applications and ordered clothes. All of these actions involved the sort of data exchanges that today's information-based tech companies crave. Applying machine learning tools to personal data can uncover valuable knowledge and generate tremendous business value. With data increasingly seen as "the new oil," many economists, politicians, and others are suggesting people should be paid for the data they produce.