Visual Analytics for Guiding Feature Attribution Method Selection

Silva, Priscylla

doi:10.24963/ijcai.2025/1243

Visual Analytics for Guiding Feature Attribution Method Selection

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Doctoral Consortium. Pages 10977-10978.

https://doi.org/10.24963/ijcai.2025/1243

Keywords

AI Ethics, Trust, Fairness: ETF: Explainability and interpretability
AI Ethics, Trust, Fairness: ETF: Trustworthy AI

Abstract

Feature attribution methods explain model predictions by assigning importance to input features. Choosing the most suitable method is difficult due to inconsistencies and a lack of universal solutions. Our research focuses on proposing tools and methodologies for evaluating, comparing, and selecting these methods.

Priscylla Silva. 2025. Visual Analytics for Guiding Feature Attribution Method Selection. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10977–10978. https://doi.org/10.24963/ijcai.2025/1243

@inproceedings{ijcai2025p1243,
  title     = {Visual Analytics for Guiding Feature Attribution Method Selection},
  author    = {Silva, Priscylla},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10977--10978},
  year      = {2025},
  month     = {8},
  note      = {Doctoral Consortium},
  doi       = {10.24963/ijcai.2025/1243},
  url       = {https://doi.org/10.24963/ijcai.2025/1243},
}

TY  - CPAPER
TI  - Visual Analytics for Guiding Feature Attribution Method Selection
AU  - Silva, Priscylla
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10977
EP  - 10978
DO  - 10.24963/ijcai.2025/1243
UR  - https://doi.org/10.24963/ijcai.2025/1243
ER  -