3 citations · 10 across the 18 of their papers we have counts for
20 papers
Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark
Steve Azzolin, Francesco Paolo Nerini, Stefano Teso +4
Explainers for Graph Neural Networks (GNNs) are commonly evaluated by their plausibility, i.e., how well their explanations recover a predefined ground truth, such as a motif plant…
Are Concept Bottleneck Models Effective as Decision-Support Systems?
Alessandro Bogani, Nicola Debole, Emanuele Marconato +3
Concept Bottleneck Models (CBMs) are interpretable-by-design neural networks that detect human-understandable concepts from the input and use them to generate predictions. By allow…
Divide et Calibra: Multiclass Local Calibration via Vector Quantization
Cesare Barbera, Lorenzo Perini, Giovanni De Toni +2
Accurate and well-calibrated Machine Learning (ML) models are mandatory in high-stakes settings, yet effective multiclass calibration remains challenging: global approaches assume…
Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
Nicola Debole, Andrea Passerini, Stefano Teso +2
Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the conc…
Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
Samuele Bortolotti, Emanuele Marconato, Andrea Pugnana +2
Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reliability in high-stakes applica…
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…
Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
Emanuele Marconato, Samuele Bortolotti, Emile van Krieken +6
Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.g. safety or structural constraints. As such, it represents…
Personalized Interpretability -- Interactive Alignment of Prototypical Parts Networks
Tomasz Michalski, Adam Wróbel, Andrea Bontempelli +6
Concept-based interpretable neural networks have gained significant attention due to their intuitive and easy-to-understand explanations based on case-based reasoning, such as "thi…
If Concept Bottlenecks are the Question, are Foundation Models the Answer?
Nicola Debole, Pietro Barbiero, Francesco Giannini +3
Concept Bottleneck Models (CBMs) are neural networks designed to conjoin high performance with ante-hoc interpretability. CBMs work by first mapping inputs (e.g., images) to high-l…
A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfaction
Leander Kurscheidt, Paolo Morettin, Roberto Sebastiani +2
In safety-critical applications, guaranteeing the satisfaction of constraints over continuous environments is crucial, e.g., an autonomous agent should never crash into obstacles o…
Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
Samuele Bortolotti, Emanuele Marconato, Paolo Morettin +2
Concept-based Models are neural networks that learn a concept extractor to map inputs to high-level concepts and an inference layer to translate these into predictions. Ensuring th…
Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective
Steve Azzolin, Sagar Malhotra, Andrea Passerini +1
Self-Explainable Graph Neural Networks (SE-GNNs) are popular explainable-by-design GNNs, but their explanations' properties and limitations are not well understood. Our first contr…
Benchmarking XAI Explanations with Human-Aligned Evaluations
Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier +9
We introduce PASTA (Perceptual Assessment System for explanaTion of Artificial Intelligence), a novel human-centric framework for evaluating eXplainable AI (XAI) techniques in comp…
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…
Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
Steve Azzolin, Antonio Longa, Stefano Teso +1
As Graph Neural Networks (GNNs) become more pervasive, it becomes paramount to build reliable tools for explaining their predictions. A core desideratum is that explanations are \t…
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
Samuele Bortolotti, Emanuele Marconato, Tommaso Carraro +5
The advent of powerful neural classifiers has increased interest in problems that require both learning and reasoning. These problems are critical for understanding important prope…
Semantic Loss Functions for Neuro-Symbolic Structured Prediction
Kareem Ahmed, Stefano Teso, Paolo Morettin +8
Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the in…
Learning To Guide Human Decision Makers With Vision-Language Models
Debodeep Banerjee, Stefano Teso, Burcu Sayin +1
There is growing interest in AI systems that support human decision-making in high-stakes domains (e.g., medical diagnosis) to improve decision quality and reduce cognitive load. M…
BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
Emanuele Marconato, Samuele Bortolotti, Emile van Krieken +3
Neuro-Symbolic (NeSy) predictors that conform to symbolic knowledge - encoding, e.g., safety constraints - can be affected by Reasoning Shortcuts (RSs): They learn concepts consist…
Probabilistic ML Verification via Weighted Model Integration
Paolo Morettin, Andrea Passerini, Roberto Sebastiani
In machine learning (ML) verification, the majority of procedures are non-quantitative and therefore cannot be used for verifying probabilistic models, or be applied in domains whe…