Program
Monday, May 27
❖ Pre-workshop
➢ Proof of concept special session (10:30-12:30)
➢ Lunch break (12:30-13:45)
❖ First Day
➢ Introduction (13:45-14:00)
➢ Keynote Session (14:00-15:00)
■ Speaker: Bruno Carballa Smichowski
■ Speaker: Nathalie Baracaldo [online]
➢ Paper session (15:00-16:30), 20-minute presentation + 10 Q&A
● Roberto Leombruni, Federated Learning for policy evaluation: a privacy-preserving collaborative environment for causal data modelling
● Giovanni Cerulli, Data-driven policy learning, the role of FOSSR
● Alessandro Buratto, Strategic Participatory Sensing for Age of Federated Information in Privacy and Energy Aware Scenarios
➢ Coffee Break (16:30-17:00)
➢ Paper session (17:00-18:30), 20/10-minute presentation + 10/5 Q&A
●Carlos Daniel Santos, Machine Learning Counterfactual Imputation with Endogenous Covariates: The Pandemic’s Effect on Peer-to-Peer Accommodation
● Raffaele Perego, Learning to Rank for Non-Independent and Identically Distributed Datasets
● Fabrizio Patriarca, Federated Learning for the Analysis of Educational and Labor Market Trajectories of Italian University Students
● Gergely Németh, Observations of Using Model Complexity Reduction as a Defense Against Membership Retrieval [online]
➢ Social Dinner (19:00)
Tuesday, May 28
❖ Second Day
➢ Keynote Session (TBA) (9:30-10:30)
■ Speaker: Gabriele Tolomei
■ Speaker: Jermain Kaminski
➢ Coffee Break (10:30-11:00)
➢ Paper session (11:00-12:30), 20-minute presentation + 10 Q&A
● Maria Cristina Maurizio, Machine learning for the Italian public employment system
● John Darrell Van Horn, Pain and Pleasure in Human Neuroimaging Data Sharing
● Junaid Ahmed, Classifying Bot and Human Driven Content Among Pro and Anti Communities of Vaccine and Environmental Activism
➢ Social Lunch (12:30-14:00)
➢ Paper session (14:00-15:30), 20-minute presentation + 10 Q&A
● Ge Zheng, An Adaptive Federated Learning System for Information Sharing in Supply Chains
● Brian Wright, Evolution of Data Science as an Academic Field
● José A. Cafiero, Analyzing export performance using machine learning models [online]
➢ Final remarks and farewell (15:30)