5 papers
Reinforcement Learning for Durable Algorithmic Recourse
Marina Ceccon, Alessandro Fabris, Goran Radanović +2
Algorithmic recourse seeks to provide individuals with actionable recommendations that increase their chances of receiving favorable outcomes from automated decision systems (e.g.,…
A Fairness-Oriented Multi-Objective Reinforcement Learning approach for Autonomous Intersection Management
Matteo Cederle, Marco Fabris, Gian Antonio Susto
This study introduces a novel multi-objective reinforcement learning (MORL) approach for autonomous intersection management, aiming to balance traffic efficiency and environmental…
Underrepresentation, Label Bias, and Proxies: Towards Data Bias Profiles for the EU AI Act and Beyond
Marina Ceccon, Giandomenico Cornacchia, Davide Dalle Pezze +2
Undesirable biases encoded in the data are key drivers of algorithmic discrimination. Their importance is widely recognized in the algorithmic fairness literature, as well as legis…
Simple and Effective Specialized Representations for Fair Classifiers
Alberto Sinigaglia, Davide Sartor, Marina Ceccon +1
Fair classification is a critical challenge that has gained increasing importance due to international regulations and its growing use in high-stakes decision-making settings. Exis…
Latent Distillation for Continual Object Detection at the Edge
Francesco Pasti, Marina Ceccon, Davide Dalle Pezze +4
While numerous methods achieving remarkable performance exist in the Object Detection literature, addressing data distribution shifts remains challenging. Continual Learning (CL) o…