Global Counterfactual Explanations: Investigations, Implementations and Improvements
원문 초록
Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding. However, the major shortcoming associated with these methods is their inability to provide explanations beyond the local or instance-level. While some works touch upon the notion of a global explanation, typically suggesting to aggregate masses of local explanations in the hope of ascertaining global properties, few provide frameworks that are either reliable or computationally tractable. Meanwhile, practitioners are requesting more efficient and interactive explainability tools. We take this opportunity to investigate existing global methods, with a focus on implementing and improving Actionable Recourse Summaries (AReS), the only known global counterfactual explanation framework for recourse.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Graph Style Transfer for Counterfactual Explainability
Finding Counterfactual Evidences for Node Classification
Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective
Towards Fairness Assessment of Dutch Hate Speech Detection
Causality and "In-the-Wild" Video-Based Person Re-ID: A Survey
Soft Weighted Machine Unlearning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.