Andrea Passerini

research

∙ 09/14/2023

Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learning

Focus in Explainable AI is shifting from explanations defined in terms o...

0 Emanuele Marconato, et al. ∙

research

∙ 08/11/2023

Learning to Guide Human Experts via Personalized Large Language Models

In learning to defer, a predictor identifies risky decisions and defers ...

0 Debodeep Banerjee, et al. ∙

research

∙ 06/14/2023

Adaptation of Student Behavioural Routines during COVID-19: A Multimodal Approach

One population group that had to significantly adapt and change their be...

0 Nicolò A. Girardini, et al. ∙

research

∙ 05/31/2023

Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts

Neuro-Symbolic (NeSy) predictive models hold the promise of improved com...

0 Emanuele Marconato, et al. ∙

research

∙ 05/09/2023

Egocentric Hierarchical Visual Semantics

We are interested in aligning how people think about objects and what ma...

0 Luca Erculiani, et al. ∙

research

∙ 03/31/2023

Interval Logic Tensor Networks

In this paper, we introduce Interval Real Logic (IRL), a two-sorted logi...

0 Samy Badreddine, et al. ∙

research

∙ 03/22/2023

Neuro-Symbolic Reasoning Shortcuts: Mitigation Strategies and their Limitations

Neuro-symbolic predictors learn a mapping from sub-symbolic inputs to hi...

0 Emanuele Marconato, et al. ∙

research

∙ 02/13/2023

Enhancing SMT-based Weighted Model Integration by Structure Awareness

The development of efficient exact and approximate algorithms for probab...

0 Giuseppe Spallitta, et al. ∙

research

∙ 02/02/2023

Neuro Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal

We introduce Neuro-Symbolic Continual Learning, where a model has to sol...

0 Emanuele Marconato, et al. ∙

research

∙ 02/02/2023

Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities

Graph Neural Networks (GNNs) have become the leading paradigm for learni...

0 Antonio Longa, et al. ∙

research

∙ 10/27/2022

Explaining the Explainers in Graph Neural Networks: a Comparative Study

Following a fast initial breakthrough in graph based learning, Graph Neu...

0 Antonio Longa, et al. ∙

research

∙ 10/13/2022

Global Explainability of GNNs via Logic Combination of Learned Concepts

While instance-level explanation of GNN is a well-studied problem with p...

0 Steve Azzolin, et al. ∙

research

∙ 06/28/2022

SMT-based Weighted Model Integration with Structure Awareness

Weighted Model Integration (WMI) is a popular formalism aimed at unifyin...

0 Giuseppe Spallitta, et al. ∙

research

∙ 05/31/2022

Concept-level Debugging of Part-Prototype Networks

Part-prototype Networks (ProtoPNets) are concept-based classifiers desig...

0 Andrea Bontempelli, et al. ∙

research

∙ 05/31/2022

GlanceNets: Interpretabile, Leak-proof Concept-based Models

There is growing interest in concept-based models (CBMs) that combine hi...

0 Emanuele Marconato, et al. ∙

research

∙ 05/27/2022

Generating personalized counterfactual interventions for algorithmic recourse by eliciting user preferences

Counterfactual interventions are a powerful tool to explain the decision...

0 Giovanni De Toni, et al. ∙

research

∙ 05/20/2022

Machine Learning for Combinatorial Optimisation of Partially-Specified Problems: Regret Minimisation as a Unifying Lens

It is increasingly common to solve combinatorial optimisation problems t...

0 Stefano Teso, et al. ∙

research

∙ 05/18/2022

Neighbourhood matching creates realistic surrogate temporal networks

Temporal networks are essential for modeling and understanding systems w...

0 Antonio Longa, et al. ∙

research

∙ 01/18/2022

Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis

Being able to provide counterfactual interventions - sequences of action...

0 Giovanni De Toni, et al. ∙

research

∙ 11/11/2021

The Science of Rejection: A Research Area for Human Computation

We motivate why the science of learning to reject model predictions is c...

32 Burcu Sayin, et al. ∙

research

∙ 10/04/2021

An Efficient Procedure for Mining Egocentric Temporal Motifs

Temporal graphs are structures which model relational data between entit...

0 Antonio Longa, et al. ∙

research

∙ 09/23/2021

Toward a Unified Framework for Debugging Gray-box Models

We are concerned with debugging concept-based gray-box models (GBMs). Th...

0 Andrea Bontempelli, et al. ∙

research

∙ 09/01/2021

Learning compositional programs with arguments and sampling

One of the most challenging goals in designing intelligent systems is em...

0 Giovanni De Toni, et al. ∙

research

∙ 06/07/2021

Interactive Label Cleaning with Example-based Explanations

We tackle sequential learning under label noise in applications where a ...

0 Stefano Teso, et al. ∙

research

∙ 04/26/2021

Towards Visual Semantics

In Visual Semantics we study how humans build mental representations, i....

0 Fausto Giunchiglia, et al. ∙

research

∙ 03/31/2021

Neuro-Symbolic Constraint Programming for Structured Prediction

We propose Nester, a method for injecting neural networks into constrain...

0 Paolo Dragone, et al. ∙

research

∙ 03/27/2021

Human-in-the-loop Handling of Knowledge Drift

We introduce and study knowledge drift (KD), a complex form of drift tha...

0 Andrea Bontempelli, et al. ∙

research

∙ 01/28/2021

Generalising via Meta-Examples for Continual Learning in the Wild

Learning quickly and continually is still an ambitious task for neural n...

4 Alessia Bertugli, et al. ∙

research

∙ 12/15/2020

Learning Aggregation Functions

Learning on sets is increasingly gaining attention in the machine learni...

0 Giovanni Pellegrini, et al. ∙

research

∙ 11/02/2020

Learning in the Wild with Incremental Skeptical Gaussian Processes

The ability to learn from human supervision is fundamental for personal ...

0 Andrea Bontempelli, et al. ∙

research

∙ 09/17/2020

Few-Shot Unsupervised Continual Learning through Meta-Examples

In real-world applications, data do not reflect the ones commonly used f...

46 Alessia Bertugli, et al. ∙

research

∙ 07/26/2020

Efficient Generation of Structured Objects with Constrained Adversarial Networks

Generative Adversarial Networks (GANs) struggle to generate structured o...

0 Luca Di Liello, et al. ∙

research

∙ 04/10/2020

Give more data, awareness and control to individual citizens, and they will help COVID-19 containment

The rapid dynamics of COVID-19 calls for quick and effective tracking of...

0 Mirco Nanni, et al. ∙

research

∙ 12/06/2019

Continual egocentric object recognition

We are interested in the problem of continual object recognition in a se...

0 Luca Erculiani, et al. ∙

research

∙ 11/22/2017

Decomposition Strategies for Constructive Preference Elicitation

We tackle the problem of constructive preference elicitation, that is th...

0 Paolo Dragone, et al. ∙

research

∙ 11/21/2017

Constructive Preference Elicitation over Hybrid Combinatorial Spaces

Peference elicitation is the task of suggesting a highly preferred confi...

0 Paolo Dragone, et al. ∙

research

∙ 12/06/2016

Coactive Critiquing: Elicitation of Preferences and Features

When faced with complex choices, users refine their own preference crite...

0 Stefano Teso, et al. ∙

research

∙ 06/17/2016

Interpretability in Linear Brain Decoding

Improving the interpretability of brain decoding approaches is of primar...

0 Seyed Mostafa Kia, et al. ∙

research

∙ 04/20/2016

Constructive Preference Elicitation by Setwise Max-margin Learning

In this paper we propose an approach to preference elicitation that is s...

0 Stefano Teso, et al. ∙

research

∙ 08/18/2015

Learning Modulo Theories for preference elicitation in hybrid domains

This paper introduces CLEO, a novel preference elicitation algorithm cap...

0 Paolo Campigotto, et al. ∙

research

∙ 05/07/2014

Structured Learning Modulo Theories

Modelling problems containing a mixture of Boolean and numerical variabl...

0 Stefano Teso, et al. ∙

research

∙ 02/18/2014

Hybrid SRL with Optimization Modulo Theories

Generally speaking, the goal of constructive learning could be seen as, ...

0 Stefano Teso, et al. ∙

Andrea Passerini

Featured Co-authors