arXiv:2107.10159
Answer-Set Programs for Reasoning about Counterfactual Interventions and Responsibility Scores for Classification
원문 초록
We describe how answer-set programs can be used to declaratively specify counterfactual interventions on entities under classification, and reason about them. In particular, they can be used to define and compute responsibility scores as attribution-based explanations for outcomes from classification models. The approach allows for the inclusion of domain knowledge and supports query answering. A detailed example with a naive-Bayes classifier is presented.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Finding Counterfactual Evidences for Node Classification
Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
Hybrid-View Attention for csPCa Classification in TRUS
Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
토론
이 논문과 연결된 포럼 글이 아직 없습니다.