5 papers
Mixture of Concept Bottleneck Experts
Francesco De Santis, Gabriele Ciravegna, Giovanni De Felice +7
Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically constrain their task predictor…
Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models
Francesco De Santis, Philippe Bich, Gabriele Ciravegna +3
To increase the trustworthiness of deep neural networks, it is critical to improve the understanding of how they make decisions. This paper introduces a novel unsupervised concept-…
V-CEM: Bridging Performance and Intervenability in Concept-based Models
Francesco De Santis, Gabriele Ciravegna, Philippe Bich +2
Concept-based eXplainable AI (C-XAI) is a rapidly growing research field that enhances AI model interpretability by leveraging intermediate, human-understandable concepts. This app…
Causally Reliable Concept Bottleneck Models
Giovanni De Felice, Arianna Casanova Flores, Francesco De Santis +4
Concept-based models are an emerging paradigm in deep learning that constrains the inference process to operate through human-interpretable variables, facilitating explainability a…
Computation of the Zero Temperature RSB parameter in Bethe Lattice Spin Glasses
Francesco De Santis, Giorgio Parisi
Bethe Lattice Spin Glasses (BLSG) are models with finite connectivity which undergo a Replica Symmetry Breaking (RSB) phase transition in field, even at zero temperature. The order…