36 citations · 82 across the 15 of their papers we have counts for
17 papers
Towards Identifying the Dataset Biases Causing Phantom Transfer
Jonas Jürß, Pietro Liò
Recent work has shown that a teacher model can transfer a bias to a student through a dataset from which every explicit reference to that bias has been filtered out, and that none…
Multimodal Attention-Aware Fusion for Diagnosing Distal Myopathy: Evaluating Model Interpretability and Clinician Trust
Mohsen Abbaspour Onari, Lucie Charlotte Magister, Yaoxin Wu +10
Distal myopathy represents a genetically heterogeneous group of skeletal muscle disorders with broad clinical manifestations, posing diagnostic challenges in radiology. To address…
Digital Histopathology with Graph Neural Networks: Concepts and Explanations for Clinicians
Alessandro Farace di Villaforesta, Lucie Charlotte Magister, Pietro Barbiero +1
To address the challenge of the ``black-box" nature of deep learning in medical settings, we combine GCExplainer - an automated concept discovery solution - along with Logic Explai…
Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts
Jonas Jürß, Lucie Charlotte Magister, Pietro Barbiero +2
Graph neural networks (GNNs) have led to major breakthroughs in a variety of domains such as drug discovery, social network analysis, and travel time estimation. However, they lack…
From Charts to Atlas: Merging Latent Spaces into One
Donato Crisostomi, Irene Cannistraci, Luca Moschella +4
Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces. We investigate in this study the aggregation of such…
Interpretable Graph Networks Formulate Universal Algebra Conjectures
Francesco Giannini, Stefano Fioravanti, Oguzhan Keskin +4
The rise of Artificial Intelligence (AI) recently empowered researchers to investigate hard mathematical problems which eluded traditional approaches for decades. Yet, the use of A…
SHARCS: Shared Concept Space for Explainable Multimodal Learning
Gabriele Dominici, Pietro Barbiero, Lucie Charlotte Magister +2
Multimodal learning is an essential paradigm for addressing complex real-world problems, where individual data modalities are typically insufficient to accurately solve a given mod…
Interpretable Neural-Symbolic Concept Reasoning
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini +7
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning…
Deep Multiple Instance Learning with Distance-Aware Self-Attention
Georg Wölflein, Lucie Charlotte Magister, Pietro Liò +2
Traditional supervised learning tasks require a label for every instance in the training set, but in many real-world applications, labels are only available for collections (bags)…
Categorical Foundations of Explainable AI: A Unifying Theory
Pietro Barbiero, Stefano Fioravanti, Francesco Giannini +3
Explainable AI (XAI) aims to address the human need for safe and reliable AI systems. However, numerous surveys emphasize the absence of a sound mathematical formalization of key X…
Extending Logic Explained Networks to Text Classification
Rishabh Jain, Gabriele Ciravegna, Pietro Barbiero +3
Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have o…
Global Explainability of GNNs via Logic Combination of Learned Concepts
Steve Azzolin, Antonio Longa, Pietro Barbiero +2
While instance-level explanation of GNN is a well-studied problem with plenty of approaches being developed, providing a global explanation for the behaviour of a GNN is much less…
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna +9
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworth…
Encoding Concepts in Graph Neural Networks
Lucie Charlotte Magister, Pietro Barbiero, Dmitry Kazhdan +5
The opaque reasoning of Graph Neural Networks induces a lack of human trust. Existing graph network explainers attempt to address this issue by providing post-hoc explanations, how…
Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis
Han Xuanyuan, Pietro Barbiero, Dobrik Georgiev +2
Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are t…
GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
Lucie Charlotte Magister, Dmitry Kazhdan, Vikash Singh +1
While graph neural networks (GNNs) have been shown to perform well on graph-based data from a variety of fields, they suffer from a lack of transparency and accountability, which h…
Algorithmic Concept-based Explainable Reasoning
Dobrik Georgiev, Pietro Barbiero, Dmitry Kazhdan +2
Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems. This has numerous benefits, su…