iml: An R package for Interpretable Machine Learning
By Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl. 2018
561 citations recorded by the source corpus.
Complex, non-parametric models, which are typically used in machine learning, have proven to be successful in many prediction tasks. But these models usually operate as black boxes: While they are good at predicting, they are often not interpretable. Many inherently interpretable models have been suggested, which come at the cost of losing predictive power. Another option is to apply interpretability methods to a black box model after model training. Given the velocity of research on new machine learning models, it is preferable to have model-agnostic tools which can be applied to a random forest as well as to a neural network. Tools for model-agnostic interpretability methods should improve the adoption of machine learning.
Subfields: Artificial Intelligence, Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Przemyslaw Biecek
- Alicja Gosiewska
- Christoph Molnar
- Giuseppe Casalicchio
- Mateusz Staniak
- Bernd Bischl
- Paul Rad
- Arun Das
In Safety, Robustness & Interpretability
- Przemyslaw Biecek
- Alicja Gosiewska
- Paul Rad
- Arun Das
- Bernd Bischl
- Christoph Molnar
- Mateusz Staniak
- Giuseppe Casalicchio
Citations in the corpus
- Visualizing the Feature Importance for Black Box Models (2018, background): “ty and interpretability [14]. Many researchers have therefore developed and implemented several model-agnostic interpretability tools, which quantify or visualize feature eects or feature importance [9, 11, 17]. In our context, the terms feature eect, feature contribution and feature attribution des”
- Explanations of model predictions with live and breakDown packages (2018, positive): “We also compare their results with existing implementations of state-of-the-art solutions, namely, lime (Pedersen and Benesty, 2018) which implements Locally Interpretable Model-agnostic Explanations and iml (Molnar et al., 2018) which implements Shapley values.”
- Do Not Trust Additive Explanations (2019, methodology): “There are several modifications of the LIME (Ribeiro et al., 2016) approach, for example live (Staniak and Biecek, 2018) and two R implementations of lime (Pedersen and Benesty, 2019; Molnar et al., 2018).”
- Interpretable Machine Learning - A Brief History, State-of-the-Art and Challenges (2020, methodology): “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.”
- Multi-Objective Counterfactual Explanations (2020, methodology): “We will provide an open source R library with our implementation of the method based on the iml package [23].”
- Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey (2020, methodology): “• IML package [113] is maintained by Christoph Molnar, author of [89].”