Searcharxiv⌕ Search

arXiv subjects

André Panisson

Publications and source records attributed to André Panisson.

At least 19 recordsLinked to original sources
arXiv2026

Inductive Correlation Clustering with Graph Neural Networks

Correlation Clustering (CC) is a natural formulation of clustering in combinatorial optimization, which uses a graph representation of the input and does not require a pre-specified number of clusters. Given $n$ objects and a pairwise similarity function, the goal is to cluster the objects so that similar objects are put in the same cluster and dissimilar objects are put in different clusters. Despite its versatility, existing CC algorithms suffer from significant scalability issues and are inherently transductive: i.e., the algorithm must be executed from scratch for any new problem instance. In this work, we bridge this gap by leveraging Graph Neural Networks (GNNs) to solve Inductive Correlation Clustering, a novel generalization of the CC problem designed to handle unseen graph instances. By learning to exploit common structural patterns and node features during training, our framework generalizes to new graphs drawn from the same distribution with minimal computational overhead with respect to standard algorithms. We demonstrate the effectiveness and scalability of our approach through extensive experiments. Our framework not only excels in the inductive setting, e.g., lowering the inference time up to $5$ order of magnitude, while maintaining an approximation ratio within $~10\%$ of the best baseline solution, but also achieves competitive results on standard (transductive) CC benchmarks. Finally, we showcase a practical application of our framework as a learnable pooling mechanism for graph classification. Our results indicate that our method serves as an efficient pooling layer, enhancing the ability of GNNs to capture hierarchical structural information in networks.

cs.LG↗
arXiv2026

The Geometry of Representational Failures in Vision Language Models

Vision-Language Models (VLMs) exhibit puzzling failures in multi-object visual tasks, such as hallucinating non-existent elements or failing to identify the most similar objects among distractions. While these errors mirror human cognitive constraints, such as the 'Binding Problem', the internal mechanisms driving them in artificial systems remain poorly understood. Here, we propose a mechanistic insight by analyzing the representational geometry of open-weight VLMs (Qwen, InternVL, Gemma), comparing methodologies to distill "concept vectors'' - latent directions encoding visual concepts. We validate our concept vectors via steering interventions that reliably manipulate model behavior in both simplified and naturalistic vision tasks (e.g., forcing the model to perceive a red flower as blue). We observe that the geometric overlap between these vectors strongly correlates with specific error patterns, offering a grounded quantitative framework to understand how internal representations shape model behavior and drive visual failures.

cs.CV↗
arXiv2026

Size-adaptive Hypothesis Testing for Fairness

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 $α$. (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.

cs.LG↗
arXiv2025

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

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, 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.

cs.AI↗
arXiv2025

Disentangled and Self-Explainable Node Representation Learning

Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining graph model decisions, the interpretability of unsupervised node embeddings remains underexplored. To bridge this gap, we introduce DiSeNE (Disentangled and Self-Explainable Node Embedding), a framework that generates self-explainable embeddings in an unsupervised manner. Our method employs disentangled representation learning to produce dimension-wise interpretable embeddings, where each dimension is aligned with distinct topological structure of the graph. We formalize novel desiderata for disentangled and interpretable embeddings, which drive our new objective functions, optimizing simultaneously for both interpretability and disentanglement. Additionally, we propose several new metrics to evaluate representation quality and human interpretability. Extensive experiments across multiple benchmark datasets demonstrate the effectiveness of our approach.

cs.LG↗
arXiv2025

Fast and Effective GNN Training through Sequences of Random Path Graphs

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 progressively refines the GNN weights on a sequence of random spanning trees suitably transformed into path graphs which, despite their simplicity, are shown to retain essential topological and node information of the original input graph. The sparse nature of these path graphs substantially lightens the computational burden of GNN training. This not only enhances scalability but also improves accuracy in subsequent test phases, especially under small training set regimes, which are of great practical importance, as in many real-world scenarios labels may be hard to obtain. In these settings, our framework yields very good results as it effectively counters the training deterioration caused by overfitting when the training set is small. Our method also addresses common issues like over-squashing and over-smoothing while avoiding under-reaching phenomena. Although our framework is flexible and can be deployed in several types of GNNs, in this paper we focus on graph convolutional networks and carry out an extensive experimental investigation on a number of real-world graph benchmarks, where we achieve simultaneous improvement of training speed and test accuracy over a wide pool of representative baselines.

cs.LG↗
arXiv2024

Multi-Class and Multi-Task Strategies for Neural Directed Link Prediction

Link Prediction is a foundational task in Graph Representation Learning, supporting applications like link recommendation, knowledge graph completion and graph generation. Graph Neural Networks have shown the most promising results in this domain and are currently the de facto standard approach to learning from graph data. However, a key distinction exists between Undirected and Directed Link Prediction: the former just predicts the existence of an edge, while the latter must also account for edge directionality and bidirectionality. This translates to Directed Link Prediction (DLP) having three sub-tasks, each defined by how training, validation and test sets are structured. Most research on DLP overlooks this trichotomy, focusing solely on the "existence" sub-task, where training and test sets are random, uncorrelated samples of positive and negative directed edges. Even in the works that recognize the aforementioned trichotomy, models fail to perform well across all three sub-tasks. In this study, we experimentally demonstrate that training Neural DLP (NDLP) models only on the existence sub-task, using methods adapted from Neural Undirected Link Prediction, results in parameter configurations that fail to capture directionality and bidirectionality, even after rebalancing edge classes. To address this, we propose three strategies that handle the three tasks simultaneously. Our first strategy, the Multi-Class Framework for Neural Directed Link Prediction (MC-NDLP) maps NDLP to a Multi-Class training objective. The second and third approaches adopt a Multi-Task perspective, either with a Multi-Objective (MO-DLP) or a Scalarized (S-DLP) strategy. Our results show that these methods outperform traditional approaches across multiple datasets and models, achieving equivalent or superior performance in addressing the three DLP sub-tasks.

cs.LG↗
arXiv2024

HOLMES: HOLonym-MEronym based Semantic inspection for Convolutional Image Classifiers

Convolutional Neural Networks (CNNs) are nowadays the model of choice in Computer Vision, thanks to their ability to automatize the feature extraction process in visual tasks. However, the knowledge acquired during training is fully subsymbolic, and hence difficult to understand and explain to end users. In this paper, we propose a new technique called HOLMES (HOLonym-MEronym based Semantic inspection) that decomposes a label into a set of related concepts, and provides component-level explanations for an image classification model. Specifically, HOLMES leverages ontologies, web scraping and transfer learning to automatically construct meronym (parts)-based detectors for a given holonym (class). Then, it produces heatmaps at the meronym level and finally, by probing the holonym CNN with occluded images, it highlights the importance of each part on the classification output. Compared to state-of-the-art saliency methods, HOLMES takes a step further and provides information about both where and what the holonym CNN is looking at, without relying on densely annotated datasets and without forcing concepts to be associated to single computational units. Extensive experimental evaluation on different categories of objects (animals, tools and vehicles) shows the feasibility of our approach. On average, HOLMES explanations include at least two meronyms, and the ablation of a single meronym roughly halves the holonym model confidence. The resulting heatmaps were quantitatively evaluated using the deletion/insertion/preservation curves. All metrics were comparable to those achieved by GradCAM, while offering the advantage of further decomposing the heatmap in human-understandable concepts, thus highlighting both the relevance of meronyms to object classification, as well as HOLMES ability to capture it. The code is available at https://github.com/FrancesC0de/HOLMES.

cs.CV↗
arXiv2023

DINE: Dimensional Interpretability of Node Embeddings

Graphs are ubiquitous due to their flexibility in representing social and technological systems as networks of interacting elements. Graph representation learning methods, such as node embeddings, are powerful approaches to map nodes into a latent vector space, allowing their use for various graph tasks. Despite their success, only few studies have focused on explaining node embeddings locally. Moreover, global explanations of node embeddings remain unexplored, limiting interpretability and debugging potentials. We address this gap by developing human-understandable explanations for dimensions in node embeddings. Towards that, we first develop new metrics that measure the global interpretability of embedding vectors based on the marginal contribution of the embedding dimensions to predicting graph structure. We say that an embedding dimension is more interpretable if it can faithfully map to an understandable sub-structure in the input graph - like community structure. Having observed that standard node embeddings have low interpretability, we then introduce DINE (Dimension-based Interpretable Node Embedding), a novel approach that can retrofit existing node embeddings by making them more interpretable without sacrificing their task performance. We conduct extensive experiments on synthetic and real-world graphs and show that we can simultaneously learn highly interpretable node embeddings with effective performance in link prediction.

cs.LG↗
arXiv2023

Evaluating Link Prediction Explanations for Graph Neural Networks

Graph Machine Learning (GML) has numerous applications, such as node/graph classification and link prediction, in real-world domains. Providing human-understandable explanations for GML models is a challenging yet fundamental task to foster their adoption, but validating explanations for link prediction models has received little attention. In this paper, we provide quantitative metrics to assess the quality of link prediction explanations, with or without ground-truth. State-of-the-art explainability methods for Graph Neural Networks are evaluated using these metrics. We discuss how underlying assumptions and technical details specific to the link prediction task, such as the choice of distance between node embeddings, can influence the quality of the explanations.

cs.LG↗
arXiv2023

Beyond One-Hot-Encoding: Injecting Semantics to Drive Image Classifiers

Images are loaded with semantic information that pertains to real-world ontologies: dog breeds share mammalian similarities, food pictures are often depicted in domestic environments, and so on. However, when training machine learning models for image classification, the relative similarities amongst object classes are commonly paired with one-hot-encoded labels. According to this logic, if an image is labelled as 'spoon', then 'tea-spoon' and 'shark' are equally wrong in terms of training loss. To overcome this limitation, we explore the integration of additional goals that reflect ontological and semantic knowledge, improving model interpretability and trustworthiness. We suggest a generic approach that allows to derive an additional loss term starting from any kind of semantic information about the classification label. First, we show how to apply our approach to ontologies and word embeddings, and discuss how the resulting information can drive a supervised learning process. Second, we use our semantically enriched loss to train image classifiers, and analyse the trade-offs between accuracy, mistake severity, and learned internal representations. Finally, we discuss how this approach can be further exploited in terms of explainability and adversarial robustness. Code repository: https://github.com/S1M0N38/semantic-encodings

cs.CV↗
arXiv2023

GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the Language of Motifs

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 output. This forces the explanation language to match the classifier's feature space. However, when dealing with graph data, in which the basic features correspond to the edges describing the graph structure, this matching between features space and explanation language might not be appropriate. Decoupling the feature space (edges) from a desired high-level explanation language (such as motifs) is thus a major challenge towards developing actionable explanations for graph classification tasks. In this paper we introduce GRAPHSHAP, a Shapley-based approach able to provide motif-based explanations for identity-aware graph classifiers, assuming no knowledge whatsoever about the model or its training data: the only requirement is that the classifier can be queried as a black-box at will. For the sake of computational efficiency we explore a progressive approximation strategy and show how a simple kernel can efficiently approximate explanation scores, thus allowing GRAPHSHAP to scale on scenarios with a large explanation space (i.e. large number of motifs). We showcase GRAPHSHAP on a real-world brain-network dataset consisting of patients affected by Autism Spectrum Disorder and a control group. Our experiments highlight how the classification provided by a black-box model can be effectively explained by few connectomics patterns.

cs.LG↗
arXiv2023

The Thin Ideology of Populist Advertising on Facebook during the 2019 EU Elections

Social media has been an important tool in the expansion of the populist message, and it is thought to have contributed to the electoral success of populist parties in the past decade. This study compares how populist parties advertised on Facebook during the 2019 European Parliamentary election. In particular, we examine commonalities and differences in which audiences they reach and on which issues they focus. By using data from Meta (previously Facebook) Ad Library, we analyze 45k ad campaigns by 39 parties, both populist and mainstream, in Germany, United Kingdom, Italy, Spain, and Poland. While populist parties represent just over 20% of the total expenditure on political ads, they account for 40% of the total impressions$\unicode{x2013}$most of which from Eurosceptic and far-right parties$\unicode{x2013}$thus hinting at a competitive advantage for populist parties on Facebook. We further find that ads posted by populist parties are more likely to reach male audiences, and sometimes much older ones. In terms of issues, populist politicians focus on monetary policy, state bureaucracy and reforms, and security, while the focus on EU and Brexit is on par with non-populist, mainstream parties. However, issue preferences are largely country-specific, thus supporting the view in political science that populism is a "thin ideology", that does not have a universal, coherent policy agenda. This study illustrates the usefulness of publicly available advertising data for monitoring the populist outreach to, and engagement with, millions of potential voters, while outlining the limitations of currently available data.

cs.SI↗
arXiv2022

Global misinformation spillovers in the online vaccination debate before and during COVID-19

Anti-vaccination views pervade online social media, fueling distrust in scientific expertise and increasing vaccine-hesitant individuals. While previous studies focused on specific countries, the COVID-19 pandemic brought the vaccination discourse worldwide, underpinning the need to tackle low-credible information flows on a global scale to design effective countermeasures. Here, we leverage 316 million vaccine-related Twitter messages in 18 languages, from October 2019 to March 2021, to quantify misinformation flows between users exposed to anti-vaccination (no-vax) content. We find that, during the pandemic, no-vax communities became more central in the country-specific debates and their cross-border connections strengthened, revealing a global Twitter anti-vaccination network. U.S. users are central in this network, while Russian users also become net exporters of misinformation during vaccination roll-out. Interestingly, we find that Twitter's content moderation efforts, and in particular the suspension of users following the January 6th U.S. Capitol attack, had a worldwide impact in reducing misinformation spread about vaccines. These findings may help public health institutions and social media platforms to mitigate the spread of health-related, low-credible information by revealing vulnerable online communities.

cs.SI↗
arXiv2022

Revealing the determinants of gender inequality in urban cycling with large-scale data

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 of cycling, most countries still have a negligible uptake. This uptake is especially low for women: there is a largely unexplained, persistent gender gap in cycling. To understand the determinants of this gender gap in cycling at scale, here we use massive, automatically-collected data from the tracking application Strava on outdoor cycling for 61 cities across the United States, the United Kingdom, Italy and the Benelux area. Leveraging the associated gender and usage information, we first quantify the emerging gender gap in recreational cycling at city-level. A comparison of cycling rates of women across cities within similar geographical areas unveils a broad range of gender gaps. On a macroscopic level, we link this heterogeneity to a variety of urban indicators and provide evidence for traditional hypotheses on the determinants of the gender-cycling-gap. We find a positive association between female cycling rate and urban road safety. On a microscopic level, we identify female preferences for street-specific features in the city of New York. Enhancing the quality of the dedicated cycling infrastructure may be a way to make urban environments more accessible for women, thereby making urban transport more sustainable for everyone.

cs.CY↗
arXiv2021

Mapping urban socioeconomic inequalities in developing countries through Facebook advertising data

Ending poverty in all its forms everywhere is the number one Sustainable Development Goal of the UN 2030 Agenda. To monitor the progress towards such an ambitious target, reliable, up-to-date and fine-grained measurements of socioeconomic indicators are necessary. When it comes to socioeconomic development, novel digital traces can provide a complementary data source to overcome the limits of traditional data collection methods, which are often not regularly updated and lack adequate spatial resolution. In this study, we collect publicly available and anonymous advertising audience estimates from Facebook to predict socioeconomic conditions of urban residents, at a fine spatial granularity, in four large urban areas: Atlanta (USA), Bogotá (Colombia), Santiago (Chile), and Casablanca (Morocco). We find that behavioral attributes inferred from the Facebook marketing platform can accurately map the socioeconomic status of residential areas within cities, and that predictive performance is comparable in both high and low-resource settings. We also show that training a model on attributes of adult Facebook users, aged more than 25, leads to a more accurate mapping of socioeconomic conditions in all cities. Our work provides additional evidence of the value of social advertising media data to measure human development.

cs.CY↗
arXiv2021

Clandestino or Rifugiato? Anti-immigration Facebook Ad Targeting in Italy

Monitoring advertising around controversial issues is an important step in ensuring accountability and transparency of political processes. To that end, we use the Facebook Ads Library to collect 2312 migration-related advertising campaigns in Italy over one year. Our pro- and anti-immigration classifier (F1=0.85) reveals a partisan divide among the major Italian political parties, with anti-immigration ads accounting for nearly 15M impressions. Although composing 47.6% of all migration-related ads, anti-immigration ones receive 65.2% of impressions. We estimate that about two thirds of all captured campaigns use some kind of demographic targeting by location, gender, or age. We find sharp divides by age and gender: for instance, anti-immigration ads from major parties are 17% more likely to be seen by a male user than a female. Unlike pro-migration parties, we find that anti-immigration ones reach a similar demographic to their own voters. However their audience change with topic: an ad from anti-immigration parties is 24% more likely to be seen by a male user when the ad speaks about migration, than if it does not. Furthermore, the viewership of such campaigns tends to follow the volume of mainstream news around immigration, supporting the theory that political advertisers try to "ride the wave" of current news. We conclude with policy implications for political communication: since the Facebook Ads Library does not allow to distinguish between advertisers intentions and algorithmic targeting, we argue that more details should be shared by platforms regarding the targeting configuration of socio-political campaigns.

cs.SI↗
arXiv2020

Time-varying Graph Representation Learning via Higher-Order Skip-Gram with Negative Sampling

Representation learning models for graphs are a successful family of techniques that project nodes into feature spaces that can be exploited by other machine learning algorithms. Since many real-world networks are inherently dynamic, with interactions among nodes changing over time, these techniques can be defined both for static and for time-varying graphs. Here, we build upon the fact that the skip-gram embedding approach implicitly performs a matrix factorization, and we extend it to perform implicit tensor factorization on different tensor representations of time-varying graphs. We show that higher-order skip-gram with negative sampling (HOSGNS) is able to disentangle the role of nodes and time, with a small fraction of the number of parameters needed by other approaches. We empirically evaluate our approach using time-resolved face-to-face proximity data, showing that the learned time-varying graph representations outperform state-of-the-art methods when used to solve downstream tasks such as network reconstruction, and to predict the outcome of dynamical processes such as disease spreading. The source code and data are publicly available at https://github.com/simonepiaggesi/hosgns.

cs.LG↗