GlanceNets: Interpretable, Leak-proof Concept-based Models

In this extended abstract, we briefly outline GlanceNets [1], a new class of deep learning classifiers that acquire high-level concepts from data and use them for both computing predictions and generating ante-hoc explanations of those predictions. In contrast with other concept-based networks, GlanceNets ensure the learned concepts, and the explanations built on them, are human interpretable, even in out-of-distribution scenarios. The core ideas at the heart of GlanceNets extend naturally to other Neuro-Symbolic architectures involving reasoning during inference.

Authors

• Emanuele Marconato
• Andrea Passerini
• Stefano Teso

Keywords

• Concept-based Models
• Concept Learning
• Representation Learning
• Explainable AI