620 citations · 1.3k across the 23 of their papers we have counts for
23 papers
Decomposing Global Feature Effects Based on Feature Interactions
Julia Herbinger, Marvin N. Wright, Thomas Nagler +2
Global feature effect methods, such as partial dependence plots, provide an intelligible visualization of the expected marginal feature effect. However, such global feature effect…
Interpretable Regional Descriptors: Hyperbox-Based Local Explanations
Susanne Dandl, Giuseppe Casalicchio, Bernd Bischl +1
This work introduces interpretable regional descriptors, or IRDs, for local, model-agnostic interpretations. IRDs are hyperboxes that describe how an observation's feature values c…
counterfactuals: An R Package for Counterfactual Explanation Methods
Susanne Dandl, Andreas Hofheinz, Martin Binder +2
Counterfactual explanation methods provide information on how feature values of individual observations must be changed to obtain a desired prediction. Despite the increasing amoun…
Algorithm-Agnostic Interpretations for Clustering
Christian A. Scholbeck, Henri Funk, Giuseppe Casalicchio
A clustering outcome for high-dimensional data is typically interpreted via post-processing, involving dimension reduction and subsequent visualization. This destroys the meaning o…
Improving Accuracy of Interpretability Measures in Hyperparameter Optimization via Bayesian Algorithm Execution
Julia Moosbauer, Giuseppe Casalicchio, Marius Lindauer +1
Despite all the benefits of automated hyperparameter optimization (HPO), most modern HPO algorithms are black-boxes themselves. This makes it difficult to understand the decision p…
REPID: Regional Effect Plots with implicit Interaction Detection
Julia Herbinger, Bernd Bischl, Giuseppe Casalicchio
Machine learning models can automatically learn complex relationships, such as non-linear and interaction effects. Interpretable machine learning methods such as partial dependence…
Marginal Effects for Non-Linear Prediction Functions
Christian A. Scholbeck, Giuseppe Casalicchio, Christoph Molnar +2
Beta coefficients for linear regression models represent the ideal form of an interpretable feature effect. However, for non-linear models and especially generalized linear models,…
Explaining Hyperparameter Optimization via Partial Dependence Plots
Julia Moosbauer, Julia Herbinger, Giuseppe Casalicchio +2
Automated hyperparameter optimization (HPO) can support practitioners to obtain peak performance in machine learning models. However, there is often a lack of valuable insights int…
Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process
Christoph Molnar, Timo Freiesleben, Gunnar König +3
Scientists and practitioners increasingly rely on machine learning to model data and draw conclusions. Compared to statistical modeling approaches, machine learning makes fewer exp…
Developing Open Source Educational Resources for Machine Learning and Data Science
Ludwig Bothmann, Sven Strickroth, Giuseppe Casalicchio +4
Education should not be a privilege but a common good. It should be openly accessible to everyone, with as few barriers as possible; even more so for key technologies such as Machi…
Decomposition of Global Feature Importance into Direct and Associative Components (DEDACT)
Gunnar König, Timo Freiesleben, Bernd Bischl +2
Global model-agnostic feature importance measures either quantify whether features are directly used for a model's predictions (direct importance) or whether they contain predictio…
Over-optimism in benchmark studies and the multiplicity of design and analysis options when interpreting their results
Christina Nießl, Moritz Herrmann, Chiara Wiedemann +2
In recent years, the need for neutral benchmark studies that focus on the comparison of methods from computational sciences has been increasingly recognised by the scientific commu…
Grouped Feature Importance and Combined Features Effect Plot
Quay Au, Julia Herbinger, Clemens Stachl +2
Interpretable machine learning has become a very active area of research due to the rising popularity of machine learning algorithms and their inherently challenging interpretabili…
Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl
We present a brief history of the field of interpretable machine learning (IML), give an overview of state-of-the-art interpretation methods, and discuss challenges. Research in IM…
General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models
Christoph Molnar, Gunnar König, Julia Herbinger +6
An increasing number of model-agnostic interpretation techniques for machine learning (ML) models such as partial dependence plots (PDP), permutation feature importance (PFI) and S…
Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approach
Christoph Molnar, Gunnar König, Bernd Bischl +1
The interpretation of feature importance in machine learning models is challenging when features are dependent. Permutation feature importance (PFI) ignores such dependencies, whic…
Component-Wise Boosting of Targets for Multi-Output Prediction
Quay Au, Daniel Schalk, Giuseppe Casalicchio +3
Multi-output prediction deals with the prediction of several targets of possibly diverse types. One way to address this problem is the so called problem transformation method. This…
Sampling, Intervention, Prediction, Aggregation: A Generalized Framework for Model-Agnostic Interpretations
Christian A. Scholbeck, Christoph Molnar, Christian Heumann +2
Model-agnostic interpretation techniques allow us to explain the behavior of any predictive model. Due to different notations and terminology, it is difficult to see how they are r…
Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability
Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl
Post-hoc model-agnostic interpretation methods such as partial dependence plots can be employed to interpret complex machine learning models. While these interpretation methods can…
Visualizing the Feature Importance for Black Box Models
Giuseppe Casalicchio, Christoph Molnar, Bernd Bischl
In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduc…
OpenML Benchmarking Suites
Bernd Bischl, Giuseppe Casalicchio, Matthias Feurer +6
Machine learning research depends on objectively interpretable, comparable, and reproducible algorithm benchmarks. We advocate the use of curated, comprehensive suites of machine l…
Multilabel Classification with R Package mlr
Philipp Probst, Quay Au, Giuseppe Casalicchio +2
We implemented several multilabel classification algorithms in the machine learning package mlr. The implemented methods are binary relevance, classifier chains, nested stacking, d…
OpenML: An R Package to Connect to the Machine Learning Platform OpenML
Giuseppe Casalicchio, Jakob Bossek, Michel Lang +6
OpenML is an online machine learning platform where researchers can easily share data, machine learning tasks and experiments as well as organize them online to work and collaborat…