Interpretable Neural-Symbolic Concept Reasoning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Interpretable Neural-Symbolic Concept Reasoning

Résumé

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 tasks based on a set of human-understandable concepts. However, state-of-the-art concept-based models rely on high-dimensional concept embedding representations which lack a clear semantic meaning, thus questioning the interpretability of their decision process. To overcome this limitation, we propose the Deep Concept Reasoner (DCR), the first interpretable concept-based model that builds upon concept embeddings. In DCR, neural networks do not make task predictions directly, but they build syntactic rule structures using concept embeddings. DCR then executes these rules on meaningful concept truth degrees to provide a final interpretable and semantically-consistent prediction in a differentiable manner. Our experiments show that DCR: (i) improves up to +25% w.r.t. state-of-the-art interpretable concept-based models on challenging benchmarks (ii) discovers meaningful logic rules matching known ground truths even in the absence of concept supervision during training, and (iii), facilitates the generation of counterfactual examples providing the learnt rules as guidance.
Fichier principal
Vignette du fichier
2023-icml-interpretable-neural-symbolic-concept-reasoning.pdf (1.8 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04244362 , version 1 (16-10-2023)

Licence

Paternité

Identifiants

Citer

Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Mateo Espinosa Zarlenga, Lucie Charlotte Magister, et al.. Interpretable Neural-Symbolic Concept Reasoning. International Conference on Machine Learning (ICML), Jul 2023, Hawaii, United States. ⟨10.48550/arXiv.2304.14068⟩. ⟨hal-04244362⟩
77 Consultations
25 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More