Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sabella, Mattia, Archetti, Alberto, Pinoli, Pietro, Matteucci, Matteo, Cappiello, Cinzia
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.03686
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912873485172736
author Sabella, Mattia
Archetti, Alberto
Pinoli, Pietro
Matteucci, Matteo
Cappiello, Cinzia
author_facet Sabella, Mattia
Archetti, Alberto
Pinoli, Pietro
Matteucci, Matteo
Cappiello, Cinzia
contents Tabular machine learning systems are frequently trained on data affected by non-uniform corruption, including noisy measurements, missing entries, and feature-specific biases. In practice, these defects are often documented only through column-level reliability indicators rather than instance-wise quality annotations, limiting the applicability of many robustness and cleaning techniques. We present QuAIL, a quality-informed training mechanism that incorporates feature reliability priors directly into the learning process. QuAIL augments existing models with a learnable feature-modulation layer whose updates are selectively constrained by a quality-dependent proximal regularizer, thereby inducing controlled adaptation across features of varying trustworthiness. This stabilizes optimization under structured corruption without explicit data repair or sample-level reweighting. Empirical evaluation across 50 classification and regression datasets demonstrates that QuAIL consistently improves average performance over neural baselines under both random and value-dependent corruption, with especially robust behavior in low-data and systematically biased settings. These results suggest that incorporating feature reliability information directly into optimization dynamics is a practical and effective approach for resilient tabular learning.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03686
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption
Sabella, Mattia
Archetti, Alberto
Pinoli, Pietro
Matteucci, Matteo
Cappiello, Cinzia
Machine Learning
Artificial Intelligence
Tabular machine learning systems are frequently trained on data affected by non-uniform corruption, including noisy measurements, missing entries, and feature-specific biases. In practice, these defects are often documented only through column-level reliability indicators rather than instance-wise quality annotations, limiting the applicability of many robustness and cleaning techniques. We present QuAIL, a quality-informed training mechanism that incorporates feature reliability priors directly into the learning process. QuAIL augments existing models with a learnable feature-modulation layer whose updates are selectively constrained by a quality-dependent proximal regularizer, thereby inducing controlled adaptation across features of varying trustworthiness. This stabilizes optimization under structured corruption without explicit data repair or sample-level reweighting. Empirical evaluation across 50 classification and regression datasets demonstrates that QuAIL consistently improves average performance over neural baselines under both random and value-dependent corruption, with especially robust behavior in low-data and systematically biased settings. These results suggest that incorporating feature reliability information directly into optimization dynamics is a practical and effective approach for resilient tabular learning.
title QuAIL: Quality-Aware Inertial Learning for Robust Training under Data Corruption
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.03686