Diverse Concept Proposals for Concept Bottleneck Models
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_ | 1866912168870412288 |
|---|---|
| author | Brown, Katrina Havasi, Marton Doshi-Velez, Finale |
| author_facet | Brown, Katrina Havasi, Marton Doshi-Velez, Finale |
| contents | Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number of human-interpretable concepts in the data, which they then use to make predictions. Learning relevant concepts from data proves to be a challenging task. The most predictive concepts may not align with expert intuition, thus, failing interpretability with no recourse. Our proposed approach identifies a number of predictive concepts that explain the data. By offering multiple alternative explanations, we allow the human expert to choose the one that best aligns with their expectation. To demonstrate our method, we show that it is able discover all possible concept representations on a synthetic dataset. On EHR data, our model was able to identify 4 out of the 5 pre-defined concepts without supervision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18059 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diverse Concept Proposals for Concept Bottleneck Models Brown, Katrina Havasi, Marton Doshi-Velez, Finale Machine Learning Concept bottleneck models are interpretable predictive models that are often used in domains where model trust is a key priority, such as healthcare. They identify a small number of human-interpretable concepts in the data, which they then use to make predictions. Learning relevant concepts from data proves to be a challenging task. The most predictive concepts may not align with expert intuition, thus, failing interpretability with no recourse. Our proposed approach identifies a number of predictive concepts that explain the data. By offering multiple alternative explanations, we allow the human expert to choose the one that best aligns with their expectation. To demonstrate our method, we show that it is able discover all possible concept representations on a synthetic dataset. On EHR data, our model was able to identify 4 out of the 5 pre-defined concepts without supervision. |
| title | Diverse Concept Proposals for Concept Bottleneck Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2412.18059 |