1 code implementation • 20 Jun 2023 • Kentaro Kanamori
To avoid this trade-off and learn an interpretable rule ensemble without degrading accuracy, we introduce a new concept of interpretability, named local interpretability, which is evaluated by the total number of rules necessary to express individual predictions made by the model, rather than to express the model itself.
no code implementations • 28 Apr 2023 • Kentaro Kanamori, Takuya Takagi, Ken Kobayashi, Yuichi Ike
Then, we propose a new framework of CE, named Counterfactual Explanation by Pairs of Imputation and Action (CEPIA), that enables users to obtain valid actions even with missing values and clarifies how actions are affected by imputation of the missing values.
no code implementations • 24 Apr 2022 • Kota Mata, Kentaro Kanamori, Hiroki Arimura
Since the seminal paper by Breiman in 2001, who pointed out a potential harm of prediction multiplicities from the view of explainable AI, global analysis of a collection of all good models, also known as a `Rashomon set,' has been attracted much attention for the last years.
1 code implementation • 22 Dec 2020 • Kentaro Kanamori, Takuya Takagi, Ken Kobayashi, Yuichi Ike, Kento Uemura, Hiroki Arimura
One of the popular methods is Counterfactual Explanation (CE), also known as Actionable Recourse, which provides a user with a perturbation vector of features that alters the prediction result.
no code implementations • 5 Jun 2019 • Kentaro Kanamori, Satoshi Hara, Masakazu Ishihata, Hiroki Arimura
In this paper, we propose a K-best model enumeration algorithm for Support Vector Machines (SVM) that given a dataset S and an integer K>0, enumerates the K-best models on S with distinct support vectors in the descending order of the objective function values in the dual SVM problem.