GlanceNets: Interpretable, Leak-proof Concept-based Models

Emanuele Marconato, Andrea Passerini, Stefano Teso

Keywords: explainable AI, concept-based models, concept leakage, causal disentanglement

TL;DR: We introduce a new class of self-explainable models based on interpretable concepts.

Abstract: There is growing interest in concept-based models (CBMs) that combine high performance and interpretability by acquiring and reasoning with a vocabulary of high-level concepts. A key requirement is that the concepts be interpretable. Existing CBMs tackle this desideratum using a variety of heuristics based on unclear notions of interpretability, and fail to acquire concepts with the intended semantics. We address this by providing a clear definition of interpretability in terms of alignment between the model’s representation and an underlying data generation process, and introduce GlanceNets, a new CBM that exploits techniques from causal disentangled representation learning and open-set recognition to achieve alignment, thus improving the interpretability of the learned concepts. We show that GlanceNets, paired with concept-level supervision, achieve better alignment than state-of-the-art approaches while preventing spurious information from unintendedly leaking into the learned concepts.