activity
20172025
most citedInterpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking

122 citations · 123 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG2025

COMBINEX: A Unified Counterfactual Explainer for Graph Neural Networks via Node Feature and Structural Perturbations

Flavio Giorgi, Fabrizio Silvestri, Gabriele Tolomei

Counterfactual explanations have emerged as a powerful tool to unveil the opaque decision-making processes of graph neural networks (GNNs). However, existing techniques primarily f…

cs.OS2022

MUSTACHE: Multi-Step-Ahead Predictions for Cache Eviction

Gabriele Tolomei, Lorenzo Takanen, Fabio Pinelli

In this work, we propose MUSTACHE, a new page cache replacement algorithm whose logic is learned from observed memory access requests rather than fixed like existing policies. We f…

cs.LG20221 cited

Sparse Vicious Attacks on Graph Neural Networks

Giovanni Trappolini, Valentino Maiorca, Silvio Severino +3

Graph Neural Networks (GNNs) have proven to be successful in several predictive modeling tasks for graph-structured data. Amongst those tasks, link prediction is one of the fundame…

cs.NE2021

NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks

Federico Siciliano, Maria Sofia Bucarelli, Gabriele Tolomei +1

In this work, we formulate NEWRON: a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neuron…

cs.LG2019

Treant: Training Evasion-Aware Decision Trees

Stefano Calzavara, Claudio Lucchese, Gabriele Tolomei +2

Despite its success and popularity, machine learning is now recognized as vulnerable to evasion attacks, i.e., carefully crafted perturbations of test inputs designed to force pred…

stat.ML2017122 cited

Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking

Gabriele Tolomei, Fabrizio Silvestri, Andrew Haines +1

Machine-learned models are often described as "black boxes". In many real-world applications however, models may have to sacrifice predictive power in favour of human-interpretabil…