42 citations · 63 across the 6 of their papers we have counts for
7 papers
Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark
Steve Azzolin, Francesco Paolo Nerini, Stefano Teso +4
Explainers for Graph Neural Networks (GNNs) are commonly evaluated by their plausibility, i.e., how well their explanations recover a predefined ground truth, such as a motif plant…
Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity
Andrew Bell, Joao Fonseca, Carlo Abrate +2
Algorithmic recourse -- providing recommendations to those affected negatively by the outcome of an algorithmic system on how they can take action and change that outcome -- has ga…
Setting the Right Expectations: Algorithmic Recourse Over Time
Joao Fonseca, Andrew Bell, Carlo Abrate +2
Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take…
Counterfactual Explanations for Graph Classification Through the Lenses of Density
Carlo Abrate, Giulia Preti, Francesco Bonchi
Counterfactual examples have emerged as an effective approach to produce simple and understandable post-hoc explanations. In the context of graph classification, previous work has…
Fast and Effective GNN Training through Sequences of Random Path Graphs
Francesco Bonchi, Claudio Gentile, Francesco Paolo Nerini +2
We present GERN, a novel scalable framework for training GNNs in node classification tasks, based on effective resistance, a standard tool in spectral graph theory. Our method prog…
A Survey on the Densest Subgraph Problem and Its Variants
Tommaso Lanciano, Atsushi Miyauchi, Adriano Fazzone +1
The Densest Subgraph Problem requires to find, in a given graph, a subset of vertices whose induced subgraph maximizes a measure of density. The problem has received a great deal o…
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…