DALEX: explainers for complex predictive models

By Przemyslaw Biecek. 2018

455 citations recorded by the source corpus.

Predictive modeling is invaded by elastic, yet complex methods such as neural networks or ensembles (model stacking, boosting or bagging). Such methods are usually described by a large number of parameters or hyper parameters - a price that one needs to pay for elasticity. The very number of parameters makes models hard to understand. This paper describes a consistent collection of explainers for predictive models, a.k.a. black boxes. Each explainer is a technique for exploration of a black box model. Presented approaches are model-agnostic, what means that they extract useful information from any predictive method despite its internal structure. Each explainer is linked with a specific aspect of a model. Some are useful in decomposing predictions, some serve better in understanding performance, while others are useful in understanding importance and conditional responses of a particular variable. Every explainer presented in this paper works for a single model or for a collection of models. In the latter case, models can be compared against each other. Such comparison helps to find strengths and weaknesses of different approaches and gives additional possibilities for model validation. Presented explainers are implemented in the DALEX package for R. They are based on a uniform standardized grammar of model exploration which may be easily extended. The current implementation supports the most popular frameworks for classification and regression.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Explanations of model predictions with live and breakDown packages (2018, methodology): “In addition to packages that implement single methods, in R we have also two packages with a consistent collection of explainers: DALEX (Biecek, 2018) and iml.”
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness? (2020, neutral): “, 2019) or “descriptive” (Carmona et al., 2015; Biecek, 2018) the interpretation is, or as “descriptive accuracy” (Murdoch et al.”
Interpretable Machine Learning - A Brief History, State-of-the-Art and Challenges (2020, methodology): “nterfactual explanations [63], partial dependence plots [51,50,7] and saliency maps [2]. Open source software with implementations of various IML methods is available, for example, iml [76] and DALEX [11] for R [91] and Alibi [58] and InterpretML [83] for Python. Regulation such as GDPR and the need”
pyCeterisParibus: explaining Machine Learning models with Ceteris Paribus Profiles in Python (2019, methodology): “The most known methods are Local Interpretable Model-agnostic Explanations (LIME) (Ribeiro, Singh, & Guestrin, 2016), SHapley Additive exPlanations (SHAP) (Lundberg & Lee, 2017) and Descriptive mAchine Learning EXplanations (DALEX) (Biecek, 2018).”
Explainable AI Methods - A Brief Overview (2020, methodology): “The Break-Down method (see [16, 17]) analyzes the various orders to identify and visualize interactions in the model.”