6 papers
Overcoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidance
Taraneh Younesian, Steve Azzolin, Antonio Longa +3
Graph Neural Networks (GNNs) can solve prediction tasks by unintentionally exploiting shortcuts---that is, edges, nodes, and features that correlate with but are not causal for the…
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…
Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier +2
This paper addresses explainable AI (XAI) through the lens of Concept Bottleneck Models (CBMs) that do not require explicit concept annotations, relying instead on concepts extract…
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…
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…
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…