ICIE 1.0: A Novel Tool for Interactive Contextual Interaction Explanations

Zon, Simon B. van der; Duivesteijn, Wouter; Ipenburg, Werner van; Veldsink, Jan; Pechenizkiy, Mykola

doi:10.1007/978-3-030-13463-1_6

Cited by 3 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7 B, it would be more meaningful to average over the upward and downward proceeding ICE curves separately and hence show that the average influence of feature X 2 on the target depends on an interacting feature (here: X 3 ). Work by Zon et al [125] followed a similar idea by proposing an interactive visualization tool to group Shapley values with regards to interacting features that need to be defined by the user.…”

Section: Misleading Feature Effects Due To Aggregationmentioning

confidence: 99%

General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models

Molnar

König

Herbinger

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

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. We highlight many general pitfalls of ML model interpretation, such as using interpretation techniques in the wrong context, interpreting models that do not generalize well, ignoring feature dependencies, interactions, uncertainty estimates and issues in high-dimensional settings, or making unjustified causal interpretations, and illustrate them with examples. We focus on pitfalls for global methods that describe the average model behavior, but many pitfalls also apply to local methods that explain individual predictions. Our paper addresses ML practitioners by raising awareness of pitfalls and identifying solutions for correct model interpretation, but also addresses ML researchers by discussing open issues for further research.

show abstract

Section: Misleading Feature Effects Due To Aggregationmentioning

confidence: 99%

General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models

Molnar

König

Herbinger

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Contexts are also useful to improve the interpretability of the ML models. Zon et al [63] proposed the interactive contextual interaction explanation (ICIE) framework that allows users to view explanations of each instance under different contexts. In ICIE, a context can be defined as a set of constraints to describe a subspace of the feature space.…”

Section: Context-aware Machine Learningmentioning

confidence: 99%

“…Different from the contexts defined in the supervised learning studies [35] which define contexts or contextual features based on their impact on the importance of other predictive features, contexts in this research are defined in a purely unsupervised manner. Similar to [63], we define a context T k as a set of constraints to describe a subspace of the feature space. Based on those constraints, we can decide whether an instance is covered by this context or not.…”

Section: Extracting Interpretable Contextsmentioning

confidence: 99%

XMAP: eXplainable mapping analytical process

Nguyen

Tran

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

As the number of artificial intelligence (AI) applications increases rapidly and more people will be affected by AI’s decisions, there are real needs for novel AI systems that can deliver both accuracy and explanations. To address these needs, this paper proposes a new approach called eXplainable Mapping Analytical Process (XMAP). Different from existing works in explainable AI, XMAP is highly modularised and the interpretability for each step can be easily obtained and visualised. A number of core algorithms are developed in XMAP to capture the distributions and topological structures of data, define contexts that emerged from data, and build effective representations for classification tasks. The experiments show that XMAP can provide useful and interpretable insights across analytical steps. For the binary classification task, its predictive performance is very competitive as compared to advanced machine learning algorithms in the literature. In some large datasets, XMAP can even outperform black-box algorithms without losing its interpretability.

show abstract

“…To further investigate PSORisk explanatory capability, we have conducted extra experiments to compare the interpretability of our risk scores and SHAP [10]. For these experiments, we use extreme gradient boosting (XGBoost) as the black-box classification algorithm and a SHAP explainer is used to show the impact of each feature on the model outputs.…”

Section: A Interpretability Of Obtained Risk Scoresmentioning

confidence: 99%

“…These algorithms focus on building ML models which can be easily interpreted by decision makers while achieving a strong prediction accuracy. IML is particularly popular in risk assessment problems in a wide range of critical domains such as medicine [8], [9] and finance [10]. In these problems, users are not only interested in calculating the risk but also required to understand how the risks are determined in order to provide appropriate explanations and recommendations to the parties involved.…”

Section: Introductionmentioning

confidence: 99%