Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909377583120384 |
|---|---|
| author | Carballo-Castro, Alba Laguna, Sonia Vandenhirtz, Moritz Vogt, Julia E. |
| author_facet | Carballo-Castro, Alba Laguna, Sonia Vandenhirtz, Moritz Vogt, Julia E. |
| contents | Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are generally challenging to obtain, making it crucial to leverage all their prior knowledge. By creating concept-enriched models that incorporate concept information into existing architectures, we exploit their interpretable capabilities to the fullest extent. In particular, we propose Concept-Guided Conditional Diffusion, which can generate visual representations of concepts, and Concept-Guided Prototype Networks, which can create a concept prototype dataset and leverage it to perform interpretable concept prediction. These results open up new lines of research by exploiting pre-existing information in the quest for rendering machine learning more human-understandable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_18705 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks Carballo-Castro, Alba Laguna, Sonia Vandenhirtz, Moritz Vogt, Julia E. Machine Learning Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are generally challenging to obtain, making it crucial to leverage all their prior knowledge. By creating concept-enriched models that incorporate concept information into existing architectures, we exploit their interpretable capabilities to the fullest extent. In particular, we propose Concept-Guided Conditional Diffusion, which can generate visual representations of concepts, and Concept-Guided Prototype Networks, which can create a concept prototype dataset and leverage it to perform interpretable concept prediction. These results open up new lines of research by exploiting pre-existing information in the quest for rendering machine learning more human-understandable. |
| title | Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.18705 |