Search Results for author: Kenta Takatsu

Found 4 papers, 1 papers with code

Resilience of Supervised Learning Algorithms to Discriminatory Data Perturbations

1 code implementation17 Dec 2019 Przemyslaw A. Grabowicz, Nicholas Perello, Kenta Takatsu

In this study, we i) define and model discrimination as perturbations of a data-generating process and show how discrimination can be induced via attributes correlated with the protected attributes; ii) introduce a measure of resilience of a supervised learning algorithm to potentially discriminatory data perturbations, iii) propose a novel supervised learning algorithm that inhibits discrimination, and iv) show that it is more resilient to discriminatory perturbations in synthetic and real-world datasets than state-of-the-art learning algorithms.

Decision Making

A General Framework for Counterfactual Learning-to-Rank

no code implementations30 Apr 2018 Aman Agarwal, Kenta Takatsu, Ivan Zaitsev, Thorsten Joachims

Specifically, we derive a relaxation for propensity-weighted rank-based metrics which is subdifferentiable and thus suitable for gradient-based optimization.

Counterfactual Inference Learning-To-Rank

Cannot find the paper you are looking for? You can Submit a new open access paper.