5 papers · 1 filter
RobustModelMaker: Coupling Bootstrap Stability Selection with Leakage-Safe Nested Cross-Validation for Scientific Machine Learning
Amanda S Barnard
Small-to-medium scientific datasets place machine learning pipelines under two compounding pressures. Single-run feature selection produces feature sets that change substantially u…
OverNaN: NaN-Aware Oversampling for Imbalanced Learning with Meaningful Missingness
Amanda S Barnard
Missing values are routinely treated as defects to be eliminated through deletion or imputation prior to machine learning. In many applied domains, however, missingness itself carr…
EXAGREE: Mitigating Explanation Disagreement with Stakeholder-Aligned Models
Sichao Li, Tommy Liu, Quanling Deng +1
Conflicting explanations, arising from different attribution methods or model internals, limit the adoption of machine learning models in safety-critical domains. We turn this disa…
Practical Attribution Guidance for Rashomon Sets
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…
Diverse Explanations From Data-Driven and Domain-Driven Perspectives in the Physical Sciences
Sichao Li, Xin Wang, Amanda Barnard
Machine learning methods have been remarkably successful in material science, providing novel scientific insights, guiding future laboratory experiments, and accelerating materials…