English
Related papers

Related papers: Practical Attribution Guidance for Rashomon Sets

200 papers

The Rashomon Effect, coined by Leo Breiman, describes the phenomenon that there exist many equally good predictive models for the same dataset. This phenomenon happens for many real datasets and when it does, it sparks both magic and…

We introduce an enumeration-free method based on mathematical programming to precisely characterize various properties such as fairness or sparsity within the set of "good models", known as Rashomon set. This approach is generically…

Machine Learning · Computer Science 2025-07-08 Lucas Langlade , Julien Ferry , Gabriel Laberge , Thibaut Vidal

Predictive models may generate biased predictions when classifying imbalanced datasets. This happens when the model favors the majority class, leading to low performance in accurately predicting the minority class. To address this issue,…

Machine Learning · Computer Science 2026-05-18 Mustafa Cavus , Przemysław Biecek

The Rashomon set is the set of models that perform approximately equally well on a given dataset, and the Rashomon ratio is the fraction of all models in a given hypothesis space that are in the Rashomon set. Rashomon ratios are often large…

Machine Learning · Computer Science 2023-10-31 Lesia Semenova , Harry Chen , Ronald Parr , Cynthia Rudin

The Rashomon set of equally-good models promises less discriminatory algorithms, reduced outcome homogenization, and fairer decisions through model ensembles or reconciliation. However, we argue from the perspective of allocation…

Computers and Society · Computer Science 2025-09-03 Shomik Jain , Margaret Wang , Kathleen Creel , Ashia Wilson

As machine learning and algorithmic decision making systems are increasingly being leveraged in high-stakes human-in-the-loop settings, there is a pressing need to understand the rationale of their predictions. Researchers have responded to…

Machine Learning · Computer Science 2020-12-07 Jonathan Dinu , Jeffrey Bigham , J. Zico Kolter

Modern neural networks rarely have a single way to be right. For many tasks, multiple models can achieve identical performance while relying on different features or reasoning patterns, a property known as the Rashomon Effect. However,…

Machine Learning · Computer Science 2025-11-26 Shihan Feng , Cheng Zhang , Michael Xi , Ethan Hsu , Lesia Semenova , Chudi Zhong

Methods of eXplainable Artificial Intelligence (XAI) are used in geoscientific applications to gain insights into the decision-making strategy of Neural Networks (NNs) highlighting which features in the input contribute the most to a NN…

Geophysics · Physics 2022-08-22 Antonios Mamalakis , Elizabeth A. Barnes , Imme Ebert-Uphoff

Despite the increasingly successful application of neural networks to many problems in the geosciences, their complex and nonlinear structure makes the interpretation of their predictions difficult, which limits model trust and does not…

Geophysics · Physics 2022-06-14 Antonios Mamalakis , Imme Ebert-Uphoff , Elizabeth A. Barnes

The Rashomon effect presents a significant challenge in model selection. It occurs when multiple models achieve similar performance on a dataset but produce different predictions, resulting in predictive multiplicity. This is especially…

Machine Learning · Statistics 2025-05-13 Mustafa Cavus , Przemyslaw Biecek

The Rash\=omon effect poses challenges for deriving reliable knowledge from machine learning models. This study examined the influence of sample size on explanations from models in a Rash\=omon set using SHAP. Experiments on 5 public…

Machine Learning · Computer Science 2023-08-15 Clement Poiret , Antoine Grigis , Justin Thomas , Marion Noulhiane

Quantifying variable importance is essential for answering high-stakes questions in fields like genetics, public policy, and medicine. Current methods generally calculate variable importance for a given model trained on a given dataset.…

Machine Learning · Computer Science 2024-04-03 Jon Donnelly , Srikar Katta , Cynthia Rudin , Edward P. Browne

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

Machine Learning · Computer Science 2019-11-06 Mengjiao Yang , Been Kim

Rashomon sets are model sets within one model class that perform nearly as well as a reference model from the same model class. They reveal the existence of alternative well-performing models, which may support different interpretations.…

Machine Learning · Computer Science 2026-03-17 Fiona Katharina Ewald , Martin Binder , Matthias Feurer , Bernd Bischl , Giuseppe Casalicchio

Sparse decision tree learning provides accurate and interpretable predictive models that are ideal for high-stakes applications by finding the single most accurate tree within a (soft) size limit. Rather than relying on a single "best"…

Machine Learning · Computer Science 2025-11-06 Elif Arslan , Jacobus G. M. van der Linden , Serge Hoogendoorn , Marco Rinaldi , Emir Demirović

This paper presents a novel application of explainable AI (XAI) for root-causing performance degradation in machine learning models that learn continuously from user engagement data. In such systems a single feature corruption can cause…

Machine Learning · Computer Science 2024-03-06 Ramanathan Vishnampet , Rajesh Shenoy , Jianhui Chen , Anuj Gupta

The need for explainable AI (XAI) is well established but relatively little has been published outside of the supervised learning paradigm. This paper focuses on a principled approach to applying explainability and interpretability to the…

Machine Learning · Computer Science 2022-07-26 John Sipple , Abdou Youssef

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 address this, we…

Machine Learning · Computer Science 2025-10-07 Mustafa Cavus , Jan N. van Rijn , Przemysław Biecek

Explainable Artificial Intelligence (XAI) has become increasingly significant for improving the interpretability and trustworthiness of machine learning models. While saliency maps have stolen the show for the last few years in the XAI…

Artificial Intelligence · Computer Science 2023-09-08 Antonin Poché , Lucas Hervier , Mohamed-Chafik Bakkay

In this work, we analyze an efficient sampling-based algorithm for general-purpose reachability analysis, which remains a notoriously challenging problem with applications ranging from neural network verification to safety analysis of…

Systems and Control · Electrical Eng. & Systems 2022-04-15 Thomas Lew , Lucas Janson , Riccardo Bonalli , Marco Pavone