Salvato in:
Dettagli Bibliografici
Autori principali: Banegas-Luna, Antonio Jesús, Pérez-Sánchez, Horacio, Martínez-Cortés, Carlos
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.06455
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918470347653120
author Banegas-Luna, Antonio Jesús
Pérez-Sánchez, Horacio
Martínez-Cortés, Carlos
author_facet Banegas-Luna, Antonio Jesús
Pérez-Sánchez, Horacio
Martínez-Cortés, Carlos
contents While predictive accuracy is often prioritized in machine learning (ML) models, interpretability remains essential in scientific and high-stakes domains. However, diverse interpretability algorithms frequently yield conflicting explanations, highlighting the need for consensus to harmonize results. In this study, six ML models were trained on six synthetic datasets with known ground truths, utilizing various model-agnostic interpretability techniques. Consensus explanations were generated using established methods and a novel approach: WISCA (Weighted Scaled Consensus Attributions), which integrates class probability and normalized attributions. WISCA consistently aligned with the most reliable individual method, underscoring the value of robust consensus strategies in improving explanation reliability.
format Preprint
id arxiv_https___arxiv_org_abs_2506_06455
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WISCA: A Consensus-Based Approach to Harmonizing Interpretability in Tabular Datasets
Banegas-Luna, Antonio Jesús
Pérez-Sánchez, Horacio
Martínez-Cortés, Carlos
Machine Learning
Artificial Intelligence
While predictive accuracy is often prioritized in machine learning (ML) models, interpretability remains essential in scientific and high-stakes domains. However, diverse interpretability algorithms frequently yield conflicting explanations, highlighting the need for consensus to harmonize results. In this study, six ML models were trained on six synthetic datasets with known ground truths, utilizing various model-agnostic interpretability techniques. Consensus explanations were generated using established methods and a novel approach: WISCA (Weighted Scaled Consensus Attributions), which integrates class probability and normalized attributions. WISCA consistently aligned with the most reliable individual method, underscoring the value of robust consensus strategies in improving explanation reliability.
title WISCA: A Consensus-Based Approach to Harmonizing Interpretability in Tabular Datasets
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.06455