Idioma:

Selective Explanations

Paes, Lucas Monteiro ; Wei, Dennis ; Calmon, Flavio P

Texto completo disponível

Citações Citado por

Título:
Selective Explanations
Autor: Paes, Lucas Monteiro ; Wei, Dennis ; Calmon, Flavio P
Assuntos: Computer Science - Computation and Language ; Computer Science - Computers and Society ; Computer Science - Learning
Descrição: Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, there has been increasing efforts to develop amortized explainers, where a machine learning model is trained to predict feature attribution scores with only one inference. Despite their efficiency, amortized explainers can produce inaccurate predictions and misleading explanations. In this paper, we propose selective explanations, a novel feature attribution method that (i) detects when amortized explainers generate low-quality explanations and (ii) improves these explanations using a technique called explanations with initial guess. Our selective explanation method allows practitioners to specify the fraction of samples that receive explanations with initial guess, offering a principled way to bridge the gap between amortized explainers and their high-quality counterparts.
Data de criação/publicação: 2024-05
Idioma: Inglês

Links

Voltar para lista de resultados

Anterior Resultado 3 Avançar Ir para próxima página