CohEx: A Generalized Framework for Cohort Explanation
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_ | 1866910738750111744 |
|---|---|
| author | Meng, Fanyu Liu, Xin Kong, Zhaodan Chen, Xin |
| author_facet | Meng, Fanyu Liu, Xin Kong, Zhaodan Chen, Xin |
| contents | eXplainable Artificial Intelligence (XAI) has garnered significant attention for enhancing transparency and trust in machine learning models. However, the scopes of most existing explanation techniques focus either on offering a holistic view of the explainee model (global explanation) or on individual instances (local explanation), while the middle ground, i.e., cohort-based explanation, is less explored. Cohort explanations offer insights into the explainee's behavior on a specific group or cohort of instances, enabling a deeper understanding of model decisions within a defined context. In this paper, we discuss the unique challenges and opportunities associated with measuring cohort explanations, define their desired properties, and create a generalized framework for generating cohort explanations based on supervised clustering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13190 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CohEx: A Generalized Framework for Cohort Explanation Meng, Fanyu Liu, Xin Kong, Zhaodan Chen, Xin Machine Learning Artificial Intelligence eXplainable Artificial Intelligence (XAI) has garnered significant attention for enhancing transparency and trust in machine learning models. However, the scopes of most existing explanation techniques focus either on offering a holistic view of the explainee model (global explanation) or on individual instances (local explanation), while the middle ground, i.e., cohort-based explanation, is less explored. Cohort explanations offer insights into the explainee's behavior on a specific group or cohort of instances, enabling a deeper understanding of model decisions within a defined context. In this paper, we discuss the unique challenges and opportunities associated with measuring cohort explanations, define their desired properties, and create a generalized framework for generating cohort explanations based on supervised clustering. |
| title | CohEx: A Generalized Framework for Cohort Explanation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.13190 |