The Grammar of Interactive Explanatory Model Analysis

Abstract

The growing need for in-depth analysis of predictive models leads to a series of new methods for explaining their local and global properties. Which of these methods is the best? It turns out that this is an ill-posed question. One cannot sufficiently explain a black-box machine learning model using a single method that gives only one perspective. Isolated explanations are prone to misunderstanding, leading to wrong or simplistic reasoning. This problem is known as the Rashomon effect and refers to diverse, even contradictory, interpretations of the same phenomenon. Surprisingly, most methods developed for explainable and responsible machine learning focus on a single-aspect of the model behavior. In contrast, we showcase the problem of explainability as an interactive and sequential analysis of a model. This paper proposes how different Explanatory Model Analysis (EMA) methods complement each other and discusses why it is essential to juxtapose them. The introduced process of Interactive EMA (IEMA) derives from the algorithmic side of explainable machine learning and aims to embrace ideas developed in cognitive sciences. We formalize the grammar of IEMA to describe potential human-model dialogues. It is implemented in a widely used human-centered open-source software framework that adopts interactivity, customizability and automation as its main traits. We conduct a user study to evaluate the usefulness of IEMA, which indicates that an interactive sequential analysis of a model increases the performance and confidence of human decision making.

35 pages, 17 figures, 8 tables

References in corpus (5)

• InterpretML: A Unified Framework for Machine Learning Interpretability
• One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
• Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences
• One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency
• How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations

Cited by in corpus (9)

• Adversarial attacks and defenses in explainable artificial intelligence: A survey
• survex: an R package for explaining machine learning survival models
• dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python
• Interpretable machine learning for time-to-event prediction in medicine and healthcare
• Performance is not enough: the story told by a Rashomon quartet
• On the Robustness of Global Feature Effect Explanations
• Dataset resulting from the user study on comprehensibility of explainable AI algorithms
• Explainable Artificial Intelligence Based Fault Diagnosis and Insight Harvesting for Steel Plates Manufacturing
• Do not explain without context: addressing the blind spot of model explanations