8 papers
Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encoding
Simone Piaggesi, Riccardo Guidotti, Fosca Giannotti +1
Post-hoc explainability is essential for understanding black-box machine learning models. Surrogate-based techniques are widely used for local and global model-agnostic explanation…
The Diversity Paradox revisited: Systemic Effects of Feedback Loops in Recommender Systems
Gabriele Barlacchi, Margherita Lalli, Emanuele Ferragina +3
Recommender systems shape individual choices through feedback loops in which user behavior and algorithmic recommendations coevolve over time. The systemic effects of these loops r…
A survey on the impacts of recommender systems on users, items, and human-AI ecosystems
Luca Pappalardo, Salvatore Citraro, Giuliano Cornacchia +12
Recommendation systems and assistants (in short, recommenders) influence through online platforms most actions of our daily lives, suggesting items or providing solutions based on…
A Simulation Framework for Studying Systemic Effects of Feedback Loops in Recommender Systems
Gabriele Barlacchi, Margherita Lalli, Emanuele Ferragina +2
Recommender systems continuously interact with users, creating feedback loops that shape both individual behavior and collective market dynamics. This paper introduces a simulation…
Interpretable and Fair Mechanisms for Abstaining Classifiers
Daphne Lenders, Andrea Pugnana, Roberto Pellungrini +3
Abstaining classifiers have the option to refrain from providing a prediction for instances that are difficult to classify. The abstention mechanism is designed to trade off the cl…
AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems
Clara Punzi, Roberto Pellungrini, Mattia Setzu +2
Everyday we increasingly rely on machine learning models to automate and support high-stake tasks and decisions. This growing presence means that humans are now constantly interact…