arXiv subjects

Bruno Lepri

Publications and source records attributed to Bruno Lepri.

At least 55 records · Page 3Linked to original sources

arXiv2025

Beauty and the Bias: Exploring the Impact of Attractiveness on Multimodal Large Language Models

Physical attractiveness matters. It has been shown to influence human perception and decision-making, often leading to biased judgments that favor those deemed attractive in what is referred to as the "attractiveness halo effect". While extensively studied in human judgments in a broad set of domains, including hiring, judicial sentencing or credit granting, the role that attractiveness plays in the assessments and decisions made by multimodal large language models (MLLMs) is unknown. To address this gap, we conduct an empirical study with 7 diverse open-source MLLMs evaluated on 91 socially relevant scenarios and a diverse dataset of 924 face images - corresponding to 462 individuals both with and without beauty filters applied to them. Our analysis reveals that attractiveness impacts the decisions made by MLLMs in 86.2% of the scenarios on average, demonstrating substantial bias in model behavior in what we refer to as an attractiveness bias. Similarly to humans, we find empirical evidence of the existence of the attractiveness halo effect in 94.8% of the relevant scenarios: attractive individuals are more likely to be attributed positive traits, such as intelligence or confidence, by MLLMs than unattractive individuals. Furthermore, we uncover gender, age and race biases in a significant portion of the scenarios which are also impacted by attractiveness, particularly in the case of gender, highlighting the intersectional nature of the algorithmic attractiveness bias. Our findings suggest that societal stereotypes and cultural norms intersect with perceptions of attractiveness in MLLMs in a complex manner. Our work emphasizes the need to account for intersectionality in algorithmic bias detection and mitigation efforts and underscores the challenges of addressing biases in modern MLLMs.

cs.CY↗

arXiv2025

GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction

Graph Neural Networks (GNNs) often struggle to capture the link-specific structural patterns crucial for accurate link prediction, as their node-centric message-passing schemes overlook the subgraph structures connecting a pair of nodes. Existing methods to inject such structural context either incur high computational cost or rely on simplistic heuristics (e.g., common neighbor counts) that fail to model multi-hop dependencies. We introduce SP4LP (Shortest Path for Link Prediction), a novel framework that combines GNN-based node encodings with sequence modeling over shortest paths. Specifically, SP4LP first applies a GNN to compute representations for all nodes, then extracts the shortest path between each candidate node pair and processes the resulting sequence of node embeddings using a sequence model. This design enables SP4LP to capture expressive multi-hop relational patterns with computational efficiency. Empirically, SP4LP achieves state-of-the-art performance across link prediction benchmarks. Theoretically, we prove that SP4LP is strictly more expressive than standard message-passing GNNs and several state-of-the-art structural features methods, establishing it as a general and principled approach for link prediction in graphs.

cs.LG↗

arXiv2025

You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control

Recommenders are significantly shaping online information consumption. While effective at personalizing content, these systems increasingly face criticism for propagating irrelevant, unwanted, and even harmful recommendations. Such content degrades user satisfaction and contributes to significant societal issues, including misinformation, radicalization, and erosion of user trust. Although platforms offer mechanisms to mitigate exposure to undesired content, these mechanisms are often insufficiently effective and slow to adapt to users' feedback. This paper introduces an intuitive, model-agnostic, and distribution-free method that uses conformal risk control to provably bound unwanted content in personalized recommendations by leveraging simple binary feedback on items. We also address a limitation of traditional conformal risk control approaches, i.e., the fact that the recommender can provide a smaller set of recommended items, by leveraging implicit feedback on consumed items to expand the recommendation set while ensuring robust risk mitigation. Our experimental evaluation on data coming from a popular online video-sharing platform demonstrates that our approach ensures an effective and controllable reduction of unwanted recommendations with minimal effort. The source code is available here: https://github.com/geektoni/mitigating-harm-recsys.

cs.IR↗

arXiv2025

Bridging Theory and Practice in Link Representation with Graph Neural Networks

Graph Neural Networks (GNNs) are widely used to compute representations of node pairs for downstream tasks such as link prediction. Yet, theoretical understanding of their expressive power has focused almost entirely on graph-level representations. In this work, we shift the focus to links and provide the first comprehensive study of GNN expressiveness in link representation. We introduce a unifying framework, the $k_ϕ$-$k_ρ$-$m$ framework, that subsumes existing message-passing link models and enables formal expressiveness comparisons. Using this framework, we derive a hierarchy of state-of-the-art methods and offer theoretical tools to analyze future architectures. To complement our analysis, we propose a synthetic evaluation protocol comprising the first benchmark specifically designed to assess link-level expressiveness. Finally, we ask: does expressiveness matter in practice? We use a graph symmetry metric that quantifies the difficulty of distinguishing links and show that while expressive models may underperform on standard benchmarks, they significantly outperform simpler ones as symmetry increases, highlighting the need for dataset-aware model selection.

cs.LG↗

arXiv2025

Fully-Geometric Cross-Attention for Point Cloud Registration

Point cloud registration approaches often fail when the overlap between point clouds is low due to noisy point correspondences. This work introduces a novel cross-attention mechanism tailored for Transformer-based architectures that tackles this problem, by fusing information from coordinates and features at the super-point level between point clouds. This formulation has remained unexplored primarily because it must guarantee rotation and translation invariance since point clouds reside in different and independent reference frames. We integrate the Gromov-Wasserstein distance into the cross-attention formulation to jointly compute distances between points across different point clouds and account for their geometric structure. By doing so, points from two distinct point clouds can attend to each other under arbitrary rigid transformations. At the point level, we also devise a self-attention mechanism that aggregates the local geometric structure information into point features for fine matching. Our formulation boosts the number of inlier correspondences, thereby yielding more precise registration results compared to state-of-the-art approaches. We have conducted an extensive evaluation on 3DMatch, 3DLoMatch, KITTI, and 3DCSR datasets.

cs.CV↗

arXiv2025

Community Aware Temporal Network Generation

The advantages of temporal networks in capturing complex dynamics, such as diffusion and contagion, has led to breakthroughs in real world systems across numerous fields. In the case of human behavior, face-to-face interaction networks enable us to understand the dynamics of how communities emerge and evolve in time through the interactions, which is crucial in fields like epidemics, sociological studies and urban science. However, state-of-the-art datasets suffer from a number of drawbacks, such as short time-span for data collection and a small number of participants. Moreover, concerns arise for the participants' privacy and the data collection costs. Over the past years, many successful algorithms for static networks generation have been proposed, but they often do not tackle the social structure of interactions or their temporal aspect. In this work, we extend a recent network generation approach to capture the evolution of interactions between different communities. Our method labels nodes based on their community affiliation and constructs surrogate networks that reflect the interactions of the original temporal networks between nodes with different labels. This enables the generation of synthetic networks that replicate realistic behaviors. We validate our approach by comparing structural measures between the original and generated networks across multiple face-to-face interaction datasets.

cs.SI↗

arXiv2025

Time Can Invalidate Algorithmic Recourse

Algorithmic Recourse (AR) aims to provide users with actionable steps to overturn unfavourable decisions made by machine learning predictors. However, these actions often take time to implement (e.g., getting a degree can take years), and their effects may vary as the world evolves. Thus, it is natural to ask for recourse that remains valid in a dynamic environment. In this paper, we study the robustness of algorithmic recourse over time by casting the problem through the lens of causality. We demonstrate theoretically and empirically that (even robust) causal AR methods can fail over time, except in the -- unlikely -- case that the world is stationary. Even more critically, unless the world is fully deterministic, counterfactual AR cannot be solved optimally. To account for this, we propose a simple yet effective algorithm for temporal AR that explicitly accounts for time under the assumption of having access to an estimator approximating the stochastic process. Our simulations on synthetic and realistic datasets show how considering time produces more resilient solutions to potential trends in the data distribution.

cs.LG↗

arXiv2025

Causal Disentanglement for Robust Long-tail Medical Image Generation

Counterfactual medical image generation effectively addresses data scarcity and enhances the interpretability of medical images. However, due to the complex and diverse pathological features of medical images and the imbalanced class distribution in medical data, generating high-quality and diverse medical images from limited data is significantly challenging. Additionally, to fully leverage the information in limited data, such as anatomical structure information and generate more structurally stable medical images while avoiding distortion or inconsistency. In this paper, in order to enhance the clinical relevance of generated data and improve the interpretability of the model, we propose a novel medical image generation framework, which generates independent pathological and structural features based on causal disentanglement and utilizes text-guided modeling of pathological features to regulate the generation of counterfactual images. First, we achieve feature separation through causal disentanglement and analyze the interactions between features. Here, we introduce group supervision to ensure the independence of pathological and identity features. Second, we leverage a diffusion model guided by pathological findings to model pathological features, enabling the generation of diverse counterfactual images. Meanwhile, we enhance accuracy by leveraging a large language model to extract lesion severity and location from medical reports. Additionally, we improve the performance of the latent diffusion model on long-tailed categories through initial noise optimization.

cs.CV↗

arXiv2025

Boosting Relational Deep Learning with Pretrained Tabular Models

Relational databases, organized into tables connected by primary-foreign key relationships, are a common format for organizing data. Making predictions on relational data often involves transforming them into a flat tabular format through table joins and feature engineering, which serve as input to tabular methods. However, designing features that fully capture complex relational patterns remains challenging. Graph Neural Networks (GNNs) offer a compelling alternative by inherently modeling these relationships, but their time overhead during inference limits their applicability for real-time scenarios. In this work, we aim to bridge this gap by leveraging existing feature engineering efforts to enhance the efficiency of GNNs in relational databases. Specifically, we use GNNs to capture complex relationships within relational databases, patterns that are difficult to featurize, while employing engineered features to encode temporal information, thereby avoiding the need to retain the entire historical graph and enabling the use of smaller, more efficient graphs. Our \textsc{LightRDL} approach not only improves efficiency, but also outperforms existing models. Experimental results on the RelBench benchmark demonstrate that our framework achieves up to $33\%$ performance improvement and a $526\times$ inference speedup compared to GNNs, making it highly suitable for real-time inference.

cs.DB↗

arXiv2025

Twenty Years of Personality Computing: Threats, Challenges and Future Directions

Personality Computing is a field at the intersection of Personality Psychology and Computer Science. Started in 2005, research in the field utilizes computational methods to understand and predict human personality traits. The expansion of the field has been very rapid and, by analyzing digital footprints (text, images, social media, etc.), it helped to develop systems that recognize and even replicate human personality. While offering promising applications in talent recruiting, marketing and healthcare, the ethical implications of Personality Computing are significant. Concerns include data privacy, algorithmic bias, and the potential for manipulation by personality-aware Artificial Intelligence. This paper provides an overview of the field, explores key methodologies, discusses the challenges and threats, and outlines potential future directions for responsible development and deployment of Personality Computing technologies.

cs.CL↗

arXiv2024

Predicting human cooperation: sensitizing drift-diffusion model to interaction and external stimuli

As humans perceive and actively engage with the world, we adjust our decisions in response to shifting group dynamics and are influenced by social interactions. This study aims to identify which aspects of interaction affect cooperation-defection choices. Specifically, we investigate human cooperation within the Prisoner's Dilemma game, using the Drift-Diffusion Model to describe the decision-making process. We introduce a novel Bayesian model for the evolution of the model's parameters based on the nature of interactions experienced with other players. This approach enables us to predict the evolution of the population's expected cooperation rate. We successfully validate our model using an unseen test dataset and apply it to explore three strategic scenarios: co-player manipulation, use of rewards and punishments, and time pressure. These results support the potential of our model as a foundational tool for developing and testing strategies aimed at enhancing cooperation, ultimately contributing to societal welfare.

physics.soc-ph↗

arXiv2024

Job loss disrupts individuals' mobility and their exploratory patterns

In recent years, human mobility research has discovered universal patterns capable of describing how people move. These regularities have been shown to partly depend on individual and environmental characteristics (e.g., gender, rural/urban, country). In this work, we show that life-course events, such as job loss, can disrupt individual mobility patterns. Adversely affecting individuals' well-being and potentially increasing the risk of social and economic inequalities, we show that job loss drives a significant change in the exploratory behaviour of individuals with changes that intensify over time since job loss. Our findings shed light on the dynamics of employment-related behavior at scale, providing a deeper understanding of key components in human mobility regularities. These drivers can facilitate targeted social interventions to support the most vulnerable populations.

physics.soc-ph↗

arXiv2024

SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks

Continuous control tasks often involve high-dimensional, dynamic, and non-linear environments. State-of-the-art performance in these tasks is achieved through complex closed-box policies that are effective, but suffer from an inherent opacity. Interpretable policies, while generally underperforming compared to their closed-box counterparts, advantageously facilitate transparent decision-making within automated systems. Hence, their usage is often essential for diagnosing and mitigating errors, supporting ethical and legal accountability, and fostering trust among stakeholders. In this paper, we propose SMOSE, a novel method to train sparsely activated interpretable controllers, based on a top-1 Mixture-of-Experts architecture. SMOSE combines a set of interpretable decisionmakers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts. The training is carried out via state-of-the-art Reinforcement Learning algorithms, exploiting load-balancing techniques to ensure fair expert usage. We then distill decision trees from the weights of the router, significantly improving the ease of interpretation. We evaluate SMOSE on six benchmark environments from MuJoCo: our method outperforms recent interpretable baselines and narrows the gap with noninterpretable state-of-the-art algorithms

cs.LG↗

arXiv2024

ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models

State-of-the-art 3D point cloud registration methods rely on labeled 3D datasets for training, which limits their practical applications in real-world scenarios and often hinders generalization to unseen scenes. Leveraging the zero-shot capabilities of foundation models offers a promising solution to these challenges. In this paper, we introduce ZeroReg, a zero-shot registration approach that utilizes 2D foundation models to predict 3D correspondences. Specifically, ZeroReg adopts an object-to-point matching strategy, starting with object localization and semantic feature extraction from multi-view images using foundation models. In the object matching stage, semantic features help identify correspondences between objects across views. However, relying solely on semantic features can lead to ambiguity, especially in scenes with multiple instances of the same category. To address this, we construct scene graphs to capture spatial relationships among objects and apply a graph matching algorithm to these graphs to accurately identify matched objects. Finally, computing fine-grained point-level correspondences within matched object regions using algorithms like SuperGlue and LoFTR achieves robust point cloud registration. Evaluations on benchmarks such as 3DMatch, 3DLoMatch, and ScanNet demonstrate ZeroReg's competitive performance, highlighting its potential to advance point-cloud registration by integrating semantic features from foundation models.

cs.CV↗

arXiv2024

Towards Civic Digital Twins: Co-Design the Citizen-Centric Future of Bologna

We introduce Civic Digital Twin (CDT), an evolution of Urban Digital Twins designed to support a citizen-centric transformative approach to urban planning and governance. CDT is being developed in the scope of the Bologna Digital Twin initiative, launched one year ago by the city of Bologna, to fulfill the city's political and strategic goal of adopting innovative digital tools to support decision-making and civic engagement. The CDT, in addition to its capability of sensing the city through spatial, temporal, and social data, must be able to model and simulate social dynamics in a city: the behavior, attitude, and preference of citizens and collectives and how they impact city life and transform transformation processes. Another distinctive feature of CDT is that it must be able to engage citizens (individuals, collectives, and organized civil society) and other civic stakeholders (utilities, economic actors, third sector) interested in co-designing the future of the city. In this paper, we discuss the motivations that led to the definition of the CDT, define its modeling aspects and key research challenges, and illustrate its intended use with two use cases in urban mobility and urban development.

cs.CY↗

arXiv2024

What is Beautiful is Still Good: The Attractiveness Halo Effect in the era of Beauty Filters

The impact of cognitive biases on decision-making in the digital world remains under-explored despite its well-documented effects in physical contexts. This study addresses this gap by investigating the attractiveness halo effect using AI-based beauty filters. We conduct a large-scale online user study involving 2,748 participants who rated facial images from a diverse set of 462 distinct individuals in two conditions: original and attractive after applying a beauty filter. Our study reveals that the same individuals receive statistically significantly higher ratings of attractiveness and other traits, such as intelligence and trustworthiness, in the attractive condition. We also study the impact of age, gender, and ethnicity and identify a weakening of the halo effect in the beautified condition, resolving conflicting findings from the literature and suggesting that filters could mitigate this cognitive bias. Finally, our findings raise ethical concerns regarding the use of beauty filters.

cs.HC↗

arXiv2024

Socioeconomic disparities in mobility behavior during the COVID-19 pandemic in developing countries

Mobile phone data have played a key role in quantifying human mobility during the COVID-19 pandemic. Existing studies on mobility patterns have primarily focused on regional aggregates in high-income countries, obfuscating the accentuated impact of the pandemic on the most vulnerable populations. Leveraging geolocation data from mobile-phone users and population census for 6 middle-income countries across 3 continents between March and December 2020, we uncovered common disparities in the behavioral response to the pandemic across socioeconomic groups. Users living in low-wealth neighborhoods were less likely to respond by self-isolating, relocating to rural areas, or refraining from commuting to work. The gap in the behavioral responses between socioeconomic groups persisted during the entire observation period. Among users living in low-wealth neighborhoods, those who commute to work in high-wealth neighborhoods pre-pandemic were particularly at risk of experiencing economic stress, facing both the reduction in economic activity in the high-wealth neighborhood and being more likely to be affected by public transport closures due to their longer commute distances. While confinement policies were predominantly country-wide, these results suggest that, when data to identify vulnerable individuals are not readily available, GPS-based analytics could help design targeted place-based policies to aid the most vulnerable.

physics.soc-ph↗

arXiv2024

Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations

Assessing the performance of systems to classify Multi-Party Conversations (MPC) is challenging due to the interconnection between linguistic and structural characteristics of conversations. Conventional evaluation methods often overlook variances in model behavior across different levels of structural complexity on interaction graphs. In this work, we propose a methodological pipeline to investigate model performance across specific structural attributes of conversations. As a proof of concept we focus on Response Selection and Addressee Recognition tasks, to diagnose model weaknesses. To this end, we extract representative diagnostic subdatasets with a fixed number of users and a good structural variety from a large and open corpus of online MPCs. We further frame our work in terms of data minimization, avoiding the use of original usernames to preserve privacy, and propose alternatives to using original text messages. Results show that response selection relies more on the textual content of conversations, while addressee recognition requires capturing their structural dimension. Using an LLM in a zero-shot setting, we further highlight how sensitivity to prompt variations is task-dependent.

cs.CL↗