Counterfactual Explanations of Time Varying Rankings (Student Abstract)

Ryusei Ohtani, Yuko Sakurai, Satoshi Oyama

AAAI 2025 pp. 29453-29455

doi:10.1609/AAAI.V39I28.35285 /aaai/2025/ohtani2025aaai-counterfactual/

Abstract

Counterfactual explanations in Explainable AI (XAI) identify which features to change to alter an outcome, but existing methods adjust only the features of a single agent. We present a new approach to re-evaluating rankings that is based on predictions of future features of the other agents in a ranking system. It uses an algorithm that provides a more realistic counterfactual explanation of changing the ranking of a particular agent. Computer experiments demonstrated that the proposed algorithm can capture the time variation of the entire ranking system in the inference results.

AAAI Semantic Scholar

Cite

Text

Ohtani et al. "Counterfactual Explanations of Time Varying Rankings (Student Abstract)." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I28.35285

Markdown

[Ohtani et al. "Counterfactual Explanations of Time Varying Rankings (Student Abstract)." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/ohtani2025aaai-counterfactual/) doi:10.1609/AAAI.V39I28.35285

BibTeX

@inproceedings{ohtani2025aaai-counterfactual,
  title     = {{Counterfactual Explanations of Time Varying Rankings (Student Abstract)}},
  author    = {Ohtani, Ryusei and Sakurai, Yuko and Oyama, Satoshi},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {29453-29455},
  doi       = {10.1609/AAAI.V39I28.35285},
  url       = {https://mlanthology.org/aaai/2025/ohtani2025aaai-counterfactual/}
}