8 citations · 15 across the 15 of their papers we have counts for
18 papers
When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features
Enrico Chialà, Francesco Ferrini, Antonio Longa +4
Graph Neural Networks (GNNs) commonly assume that node features are fully observed, despite missing features being pervasive in real-world applications. By leveraging the dependenc…
Rethinking Epistemic Uncertainty in Node Classification through Information Growth
Emma Meneghini, Francesco Ferrini, Bruno Lepri +2
Epistemic uncertainty should decrease as additional information about the data-generating process (DGP) becomes available to the predictor. Yet, existing graph evidential deep lear…
GNN Explanations that do not Explain and How to find Them
Steve Azzolin, Stefano Teso, Bruno Lepri +2
Explanations provided by Self-explainable Graph Neural Networks (SE-GNNs) are fundamental for understanding the model's inner workings and for identifying potential misuse of sensi…
SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models
Sebastiano Monti, Carlo Nicolini, Gianni Pellegrini +2
Although the capabilities of large language models have been increasingly tested on complex reasoning tasks, their long-horizon planning abilities have not yet been extensively inv…
Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution
Francesco Ferrini, Veronica Lachi, Antonio Longa +5
Handling missing node features is a key challenge for deploying Graph Neural Networks (GNNs) in real-world domains such as healthcare and sensor networks. Existing studies mostly a…
To Ask or Not to Ask: Learning to Require Human Feedback
Andrea Pugnana, Giovanni De Toni, Cesare Barbera +3
Developing decision-support systems that complement human performance in classification tasks remains an open challenge. A popular approach, Learning to Defer (LtD), allows a Machi…
Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
Marco Bronzini, Carlo Nicolini, Bruno Lepri +2
Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations. Current interpretability methods either focus o…
You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control
Giovanni De Toni, Erasmo Purificato, Emilia Gómez +3
Recommenders are significantly shaping online information consumption. While effective at personalizing content, these systems increasingly face criticism for propagating irrelevan…
GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction
Francesco Ferrini, Veronica Lachi, Antonio Longa +2
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 ove…
Bridging Theory and Practice in Link Representation with Graph Neural Networks
Veronica Lachi, Francesco Ferrini, Antonio Longa +3
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 expressi…
Boosting Relational Deep Learning with Pretrained Tabular Models
Veronica Lachi, Antonio Longa, Beatrice Bevilacqua +3
Relational databases, organized into tables connected by primary-foreign key relationships, are a common format for organizing data. Making predictions on relational data often inv…
Community Aware Temporal Network Generation
Nicolò Alessandro Girardini, Antonio Longa, Gaia Trebucchi +3
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 ca…
Time Can Invalidate Algorithmic Recourse
Giovanni De Toni, Stefano Teso, Bruno Lepri +1
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…
I Want to Break Free! Persuasion and Anti-Social Behavior of LLMs in Multi-Agent Settings with Social Hierarchy
Gian Maria Campedelli, Nicolò Penzo, Massimo Stefan +4
As LLM-based agents become increasingly autonomous and will more freely interact with each other, studying the interplay among them becomes crucial to anticipate emergent phenomena…
Hopfield Networks for Asset Allocation
Carlo Nicolini, Monisha Gopalan, Jacopo Staiano +1
We present the first application of modern Hopfield networks to the problem of portfolio optimization. We performed an extensive study based on combinatorial purged cross-validatio…
Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Exploration
Seyedehdelaram Esfahani, Giovanni De Toni, Bruno Lepri +3
Algorithmic Recourse aims to provide actionable explanations, or recourse plans, to overturn potentially unfavourable decisions taken by automated machine learning models. In this…
Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph
Marco Bronzini, Carlo Nicolini, Bruno Lepri +2
Large Language Models (LLMs) demonstrate an impressive capacity to recall a vast range of factual knowledge. However, understanding their underlying reasoning and internal mechanis…
The Garden of Forking Paths: Observing Dynamic Parameters Distribution in Large Language Models
Carlo Nicolini, Jacopo Staiano, Bruno Lepri +1
A substantial gap persists in understanding the reasons behind the exceptional performance of the Transformer architecture in NLP. A particularly unexplored area involves the mecha…