paper-with-me

홈 › Papers

An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning

2023-06-27 · Sebastian Müller, Vanessa Toborek, Katharina Beckh, Matthias Jakobs, Christian Bauckhage, Pascal Welke

The Rashomon Effect describes the following phenomenon: for a given dataset there may exist many models with equally good performance but with different solution strategies. The Rashomon Effect has implications for Explainable Machine Learning, especially for the comparability of explanations. We provide a unified view on three different comparison scenarios and conduct a quantitative evaluation across different datasets, models, attribution methods, and metrics. We find that hyperparameter-tuning plays a role and that metric selection matters. Our results provide empirical support for previously anecdotal evidence and exhibit challenges for both scientists and practitioners.

📄 PDF Abstract BibTeX arXiv:2306.15786

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Rashomon in the Streets: Explanation Ambiguity in Scene Understanding

2025-09-03 · Helge Spieker, Jørn Eirik Betten, Arnaud Gotlieb, Nadjib Lazaar 외 arxiv

Explainable AI (XAI) is essential for validating and trusting models in safety-critical applications like autonomous driving. However, the reliability of XAI is challenged by the Rashomon effect, where multiple, equally …

Scene UnderstandingAutonomous Driving

Practical Attribution Guidance for Rashomon Sets

2024-07-26 · Sichao Li, Amanda S. Barnard, Quanling Deng

Different prediction models might perform equally well (Rashomon set) in the same task, but offer conflicting interpretations and conclusions about the data. The Rashomon effect in the context of Explainable AI (XAI) has…

Beyond the Single-Best Model: Rashomon Partial Dependence Profile for Trustworthy Explanations in AutoML

2025-07-19 · Mustafa Cavus, Jan N. van Rijn, Przemysław Biecek arxiv

Automated machine learning systems efficiently streamline model selection but often focus on a single best-performing model, overlooking explanation uncertainty, an essential concern in human centered explainable AI. To …

Explanation Generation

Evaluating the Ability of Explanations to Disambiguate Models in a Rashomon Set

2026-01-13 · Kaivalya Rawal, Eoin Delaney, Zihao Fu, Sandra Wachter 외 arxiv

Explainable artificial intelligence (XAI) is concerned with producing explanations indicating the inner workings of models. For a Rashomon set of similarly performing models, explanations provide a way of disambiguating …

Metamorphic Testing with the Rashomon Set: Explanation Faithfulness in Machine Learning

2026-06-04 · Helge Spieker, Jørn Eirik Betten, Arnaud Gotlieb arxiv

Multiple machine learning models can achieve near-equivalent predictive performance on the same task, yet provide divergent feature-based explanations. This is called the Rashomon effect of (explainable) machine learning…

Feature Importance