Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908391077576704 |
|---|---|
| author | De Santis, Francesco Bich, Philippe Ciravegna, Gabriele Barbiero, Pietro Giordano, Danilo Cerquitelli, Tania |
| author_facet | De Santis, Francesco Bich, Philippe Ciravegna, Gabriele Barbiero, Pietro Giordano, Danilo Cerquitelli, Tania |
| contents | 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-based model for image classification, named Learnable Concept-Based Model (LCBM) which models concepts as random variables within a Bernoulli latent space. Unlike traditional methods that either require extensive human supervision or suffer from limited scalability, our approach employs a reduced number of concepts without sacrificing performance. We demonstrate that LCBM surpasses existing unsupervised concept-based models in generalization capability and nearly matches the performance of black-box models. The proposed concept representation enhances information retention and aligns more closely with human understanding. A user study demonstrates the discovered concepts are also more intuitive for humans to interpret. Finally, despite the use of concept embeddings, we maintain model interpretability by means of a local linear combination of concepts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02092 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models De Santis, Francesco Bich, Philippe Ciravegna, Gabriele Barbiero, Pietro Giordano, Danilo Cerquitelli, Tania Machine Learning Artificial Intelligence 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-based model for image classification, named Learnable Concept-Based Model (LCBM) which models concepts as random variables within a Bernoulli latent space. Unlike traditional methods that either require extensive human supervision or suffer from limited scalability, our approach employs a reduced number of concepts without sacrificing performance. We demonstrate that LCBM surpasses existing unsupervised concept-based models in generalization capability and nearly matches the performance of black-box models. The proposed concept representation enhances information retention and aligns more closely with human understanding. A user study demonstrates the discovered concepts are also more intuitive for humans to interpret. Finally, despite the use of concept embeddings, we maintain model interpretability by means of a local linear combination of concepts. |
| title | Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.02092 |