ML Anthology

Interpretable Local Concept-Based Explanation with Human Feedback to Predict All-Cause Mortality (Extended Abstract)

Radwa El Shawi, Mouaz H. Al-Mallah
IJCAI 2023 pp. 6873-6877
doi:10.24963/IJCAI.2023/774 /ijcai/2023/shawi2023ijcai-interpretable/

Abstract

Machine learning models are incorporated in different fields and disciplines, some of which require high accountability and transparency, for example, the healthcare sector. A widely used category of explanation techniques attempts to explain models' predictions by quantifying the importance score of each input feature. However, summarizing such scores to provide human-interpretable explanations is challenging. Another category of explanation techniques focuses on learning a domain representation in terms of high-level human-understandable concepts and then utilizing them to explain predictions. These explanations are hampered by how concepts are constructed, which is not intrinsically interpretable. To this end, we propose Concept-based Local Explanations with Feedback (CLEF), a novel local model agnostic explanation framework for learning a set of high-level transparent concept definitions in high-dimensional tabular data that uses clinician-labeled concepts rather than raw features.

PDF IJCAI Semantic Scholar

Cite

Text

El Shawi and Al-Mallah. "Interpretable Local Concept-Based Explanation with Human Feedback to Predict All-Cause Mortality (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/774

Markdown

[El Shawi and Al-Mallah. "Interpretable Local Concept-Based Explanation with Human Feedback to Predict All-Cause Mortality (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/shawi2023ijcai-interpretable/) doi:10.24963/IJCAI.2023/774

BibTeX

@inproceedings{shawi2023ijcai-interpretable,
  title     = {{Interpretable Local Concept-Based Explanation with Human Feedback to Predict All-Cause Mortality (Extended Abstract)}},
  author    = {El Shawi, Radwa and Al-Mallah, Mouaz H.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {6873-6877},
  doi       = {10.24963/IJCAI.2023/774},
  url       = {https://mlanthology.org/ijcai/2023/shawi2023ijcai-interpretable/}
}