106 citations · 514 across the 39 of their papers we have counts for
6 papers · 2 filters
Explaining the Explainers in Graph Neural Networks: a Comparative Study
Antonio Longa, Steve Azzolin, Gabriele Santin +4
Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting…
Personalized Algorithmic Recourse with Preference Elicitation
Giovanni De Toni, Paolo Viappiani, Stefano Teso +2
Algorithmic Recourse (AR) is the problem of computing a sequence of actions that -- once performed by a user -- overturns an undesirable machine decision. It is paramount that the…
A Framework for Verifiable and Auditable Federated Anomaly Detection
Gabriele Santin, Inna Skarbovsky, Fabiana Fournier +1
Federated Leaning is an emerging approach to manage cooperation between a group of agents for the solution of Machine Learning tasks, with the goal of improving each agent's perfor…
Reprogramming FairGANs with Variational Auto-Encoders: A New Transfer Learning Model
Beatrice Nobile, Gabriele Santin, Bruno Lepri +1
Fairness-aware GANs (FairGANs) exploit the mechanisms of Generative Adversarial Networks (GANs) to impose fairness on the generated data, freeing them from both disparate impact an…
Generating Synthetic Mobility Networks with Generative Adversarial Networks
Giovanni Mauro, Massimiliano Luca, Antonio Longa +2
The increasingly crucial role of human displacements in complex societal phenomena, such as traffic congestion, segregation, and the diffusion of epidemics, is attracting the inter…
Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
Giovanni De Toni, Bruno Lepri, Andrea Passerini
Being able to provide counterfactual interventions - sequences of actions we would have had to take for a desirable outcome to happen - is essential to explain how to change an unf…