Author name cluster

Alan Perotti

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networks

Francesco Cozzi
Marco Pangallo
Alan Perotti
André Panisson
Corrado Monti

Agent-Based Models (ABMs) are powerful tools for studying emergent properties in complex systems. In ABMs, agent behaviors are governed by local interactions and stochastic rules. However, these rules are ad hoc and, in general, non-differentiable, limiting the use of gradient-based methods for optimization, and thus integration with real-world data. We propose a novel framework to learn a differentiable surrogate of any ABM by observing its generated data. Our method combines diffusion models to capture behavioral stochasticity and graph neural networks to model agent interactions. Distinct from prior surrogate approaches, our method introduces a fundamental shift: rather than approximating system-level outputs, it models individual agent behavior directly, preserving the decentralized, bottom-up dynamics that define ABMs. We validate our approach on two ABMs (Schelling's segregation model and a Predator-Prey ecosystem) showing that it replicates individual-level patterns and accurately forecasts emergent dynamics beyond training. Our results demonstrate the potential of combining diffusion models and graph learning for data-driven ABM simulation.

PDF Details

NeurIPS Conference 2025 Conference Paper

Size-adaptive Hypothesis Testing for Fairness

Antonio Ferrara
Francesco Cozzi
Alan Perotti
André Panisson
Francesco Bonchi

Determining whether an algorithmic decision-making system discriminates against a specific demographic typically involves comparing a single point estimate of a fairness metric against a predefined threshold. This practice is statistically brittle: it ignores sampling error and treats small demographic subgroups the same as large ones. The problem intensifies in intersectional analyses, where multiple sensitive attributes are considered jointly, giving rise to a larger number of smaller groups. As these groups become more granular, the data representing them becomes too sparse for reliable estimation, and fairness metrics yield excessively wide confidence intervals, precluding meaningful conclusions about potential unfair treatments. In this paper, we introduce a unified, size-adaptive, hypothesis‑testing framework that turns fairness assessment into an evidence‑based statistical decision. Our contribution is twofold. (i) For sufficiently large subgroups, we prove a Central‑Limit result for the statistical parity difference, leading to analytic confidence intervals and a Wald test whose type‑I (false positive) error is guaranteed at level $\alpha$. (ii) For the long tail of small intersectional groups, we derive a fully Bayesian Dirichlet–multinomial estimator; Monte-Carlo credible intervals are calibrated for any sample size and naturally converge to Wald intervals as more data becomes available. We validate our approach empirically on benchmark datasets, demonstrating how our tests provide interpretable, statistically rigorous decisions under varying degrees of data availability and intersectionality.

PDF Details

TMLR Journal 2024 Journal Article

A True-to-the-model Axiomatic Benchmark for Graph-based Explainers

Corrado Monti
Paolo Bajardi
Francesco Bonchi
André Panisson
Alan Perotti

Regulators, researchers, and practitioners recognize the urgency of explainability in artificial intelligence systems, including the ones based on machine learning for graph-structured data. Despite the large number of proposals, however, a common understanding of what constitutes a good explanation is still lacking: different explainers often arrive at different conclusions on the same problem instance, making it hard for practitioners to choose among them. Furthermore, explainers often produce explanations through opaque logic hard to understand and assess -- ironically mirroring the black box nature they aim to elucidate. Recent proposals in the literature for benchmarking graph-based explainers typically involve embedding specific logic into data, training a black-box model, and then empirically assessing how well the explanation matches the embedded logic, i.e., they test truthfulness to the data. In contrast, we propose a true-to-the-model axiomatic framework for auditing explainers in the task of node classification on graphs. Our proposal hinges on the fundamental idea that an explainer should discern if a model relies on a particular feature for classifying a node. Building on this concept, we develop three types of white-box classifiers, with clear internal logic, that are relevant in real-world applications. We then formally prove that the set of features that can induce a change in the classification correctly corresponds to a ground-truth set of predefined important features. This property allows us to use the white-box classifiers to build a testing framework. We apply this framework to both synthetic and real data and evaluate various state-of-the-art explainers, thus characterizing their behavior. Our findings highlight how explainers often react in a rather counter-intuitive fashion to technical details that might be easily overlooked. Our approach offers valuable insights and recommended practices for selecting the right explainer given the task at hand, and for developing new methods for explaining graph-learning models.

PDF Details

NeSy Conference 2012 Conference Paper

Neural-Symbolic Rule-Based Monitoring

Alan Perotti
Artur S. d'Avila Garcez
Guido Boella
Daniele Rispoli

In this paper we present a neural-symbolic system for monitoring traces of observations in sofware systems. To this end, we define an algorithm that translates a RuleR rule-based monitoring system (RS) into a rule-based neural network system (RNNS). We then show how the RNNS can perform trace monitoring effectively and analyze its performance, reporting promising preliminary results. Finally, we discuss how network learning could be used within RNNS to embed the system into a framework for iterative verification and model adaptation. It is hoped that a tight integration of verification and adaptation within the neural-symbolic approach will help support the development of self-adapting, self-healing systems.

Details