89 citations · 117 across the 8 of their papers we have counts for
9 papers
Evaluating Link Prediction Explanations for Graph Neural Networks
Claudio Borile, Alan Perotti, André Panisson
Graph Machine Learning (GML) has numerous applications, such as node/graph classification and link prediction, in real-world domains. Providing human-understandable explanations fo…
Beyond One-Hot-Encoding: Injecting Semantics to Drive Image Classifiers
Alan Perotti, Simone Bertolotto, Eliana Pastor +1
Images are loaded with semantic information that pertains to real-world ontologies: dog breeds share mammalian similarities, food pictures are often depicted in domestic environmen…
Streamlining models with explanations in the learning loop
Francesco Lomuscio, Paolo Bajardi, Alan Perotti +1
Several explainable AI methods allow a Machine Learning user to get insights on the classification process of a black-box model in the form of local linear explanations. With such…
Revealing the determinants of gender inequality in urban cycling with large-scale data
Alice Battiston, Ludovico Napoli, Paolo Bajardi +4
Cycling is an outdoor activity with massive health benefits, and an effective solution towards sustainable urban transport. Despite these benefits and the recent rising popularity…
GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the Language of Motifs
Alan Perotti, Paolo Bajardi, Francesco Bonchi +1
Most methods for explaining black-box classifiers (e.g. on tabular data, images, or time series) rely on measuring the impact that removing/perturbing features has on the model out…
To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods
Elvio G. Amparore, Alan Perotti, Paolo Bajardi
The main objective of eXplainable Artificial Intelligence (XAI) is to provide effective explanations for black-box classifiers. The existing literature lists many desirable propert…
FairLens: Auditing Black-box Clinical Decision Support Systems
Cecilia Panigutti, Alan Perotti, Andrè Panisson +2
The pervasive application of algorithmic decision-making is raising concerns on the risk of unintended bias in AI systems deployed in critical settings such as healthcare. The dete…
Runtime Verification Through Forward Chaining
Alan Perotti, Guido Boella, Artur d'Avila Garcez
In this paper we present a novel rule-based approach for Runtime Verification of FLTL properties over finite but expanding traces. Our system exploits Horn clauses in implication f…
RuleRunner technical report
Alan Perotti
Rule-based run-time monitoring system for finite traces, with FLTL verdict and quadratic complexity.