Search Results for author:
Found 28 papers, 16 papers with code
Effector: A Python package for regional explanations
Effector implements well-established global effect methods, assesses the heterogeneity of each method and, based on that, provides regional effects.
Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration
We address this issue by proposing ShapleyBO, a framework for interpreting BO's proposals by game-theoretic Shapley values. They quantify each parameter's contribution to BO's acquisition function.
Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis
We argue that interpretations of machine learning (ML) models or the model-building process can bee seen as a form of sensitivity analysis (SA), a general methodology used to explain complex systems in many fields such as environmental modeling, engineering, or economics.
Leveraging Model-based Trees as Interpretable Surrogate Models for Model Distillation
Surrogate models play a crucial role in retrospectively interpreting complex and powerful black box machine learning models via model distillation.
fmeffects: An R Package for Forward Marginal Effects
Forward marginal effects (FMEs) have recently been introduced as a versatile and effective model-agnostic interpretation method.
Decomposing Global Feature Effects Based on Feature Interactions
We formally introduce generalized additive decomposition of global effects (GADGET), which is a new framework based on recursive partitioning to find interpretable regions in the feature space such that the interaction-related heterogeneity of local feature effects is minimized.
Interpretable Regional Descriptors: Hyperbox-Based Local Explanations
This work introduces interpretable regional descriptors, or IRDs, for local, model-agnostic interpretations.
counterfactuals: An R Package for Counterfactual Explanation Methods
Counterfactual explanation methods provide information on how feature values of individual observations must be changed to obtain a desired prediction.
Algorithm-Agnostic Interpretations for Clustering
The partial dependence for clustering evaluates average changes in cluster assignments for the entire feature space.
Improving Accuracy of Interpretability Measures in Hyperparameter Optimization via Bayesian Algorithm Execution
Despite all the benefits of automated hyperparameter optimization (HPO), most modern HPO algorithms are black-boxes themselves.
REPID: Regional Effect Plots with implicit Interaction Detection
Machine learning models can automatically learn complex relationships, such as non-linear and interaction effects.
Marginal Effects for Non-Linear Prediction Functions
Hence, marginal effects are typically used as approximations for feature effects, either in the shape of derivatives of the prediction function or forward differences in prediction due to a change in a feature value.
Explaining Hyperparameter Optimization via Partial Dependence Plots
Automated hyperparameter optimization (HPO) can support practitioners to obtain peak performance in machine learning models.
Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process
Scientists and practitioners increasingly rely on machine learning to model data and draw conclusions.
Developing Open Source Educational Resources for Machine Learning and Data Science
It should be openly accessible to everyone, with as few barriers as possible; even more so for key technologies such as Machine Learning (ML) and Data Science (DS).
Decomposition of Global Feature Importance into Direct and Associative Components (DEDACT)
Direct importance provides causal insight into the model's mechanism, yet it fails to expose the leakage of information from associated but not directly used variables.
Towards Explaining Hyperparameter Optimization via Partial Dependence Plots
Automated hyperparameter optimization (HPO) can support practitioners to obtain peak performance in machine learning models.
Grouped Feature Importance and Combined Features Effect Plot
However, for researchers and practitioners, it is often equally important to quantify the importance or visualize the effect of feature groups.
Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
To address the challenges and advance the field, we urge to recall our roots of interpretable, data-driven modeling in statistics and (rule-based) ML, but also to consider other areas such as sensitivity analysis, causal inference, and the social sciences.
General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models
An increasing number of model-agnostic interpretation techniques for machine learning (ML) models such as partial dependence plots (PDP), permutation feature importance (PFI) and Shapley values provide insightful model interpretations, but can lead to wrong conclusions if applied incorrectly.
Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approach
In addition, we apply the conditional subgroups approach to partial dependence plots (PDP), a popular method for describing feature effects that can also suffer from extrapolation when features are dependent and interactions are present in the model.
Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability
Post-hoc model-agnostic interpretation methods such as partial dependence plots can be employed to interpret complex machine learning models.
Sampling, Intervention, Prediction, Aggregation: A Generalized Framework for Model-Agnostic Interpretations
Model-agnostic interpretation techniques allow us to explain the behavior of any predictive model.
Component-Wise Boosting of Targets for Multi-Output Prediction
One way to address this problem is the so called problem transformation method.
Visualizing the Feature Importance for Black Box Models
Based on local feature importance, we propose two visual tools: partial importance (PI) and individual conditional importance (ICI) plots which visualize how changes in a feature affect the model performance on average, as well as for individual observations.
OpenML Benchmarking Suites
Machine learning research depends on objectively interpretable, comparable, and reproducible algorithm benchmarks.
Multilabel Classification with R Package mlr
We implemented several multilabel classification algorithms in the machine learning package mlr.
OpenML: An R Package to Connect to the Machine Learning Platform OpenML
We show how the OpenML package allows R users to easily search, download and upload data sets and machine learning tasks.
