Distribution-Aware Counterfactual Explanation by Mixed-Integer Linear Optimization

نویسندگان

چکیده

Post-hoc explanation methods for machine learning models have been widely used to support decision-making. Counterfactual Explanation (CE), also known as Actionable Recourse, is one of the post-hoc that provides a perturbation vector alters prediction result obtained from classifier. Users can directly interpret an “action” obtain their desired decision results. However, actions extracted by existing often become unrealistic users because they do not adequately consider characteristics corresponding data distribution, such feature-correlations and outlier risk. To suggest executable action users, we propose new framework CE, which refer Distribution-Aware (DACE), extracts realistic evaluating its reality on empirical distribution. Here, key idea define cost function based Mahalanobis distance local factor. Then, mixed-integer linear optimization approach extracting optimal minimizing defined function. Experiments conducted real datasets demonstrate effectiveness proposed method compared with CE methods.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Integer convex minimization by mixed integer linear optimization

Minimizing a convex function over the integral points of a bounded convex set is polynomial in fixed dimension [6]. We provide an alternative, short, and geometrically motivated proof of this result. In particular, we present an oraclepolynomial algorithm based on a mixed integer linear optimization oracle.

متن کامل

Parallel Solvers for Mixed Integer Linear Optimization

In this article, we provide an overview of the current state of the art with respect to solution of mixed integer linear optimization problems (MILPS) in parallel. Sequential algorithms for solving MILPs have improved substantially in the last two decades and commercial MILP solvers are now considered effective off-the-shelf tools for optimization. Although concerted development of parallel MIL...

متن کامل

Trajectory Optimization using Mixed-Integer Linear Programming

This thesis presents methods for finding optimal trajectories for vehicles subjected to avoidance and assignment requirements. The former include avoidance of collisions with obstacles or other vehicles and avoidance of thruster plumes from spacecraft. Assignment refers to the inclusion of decisions about terminal constraints in the optimization, such as assignment of waypoints to UAVs and the ...

متن کامل

Mixed-Integer Nonlinear Optimization

Many optimal decision problems in scientific, engineering, and public sector applications involve both discrete decisions and nonlinear system dynamics that affect the quality of the final design or plan. These decision problems lead to mixed-integer nonlinear programming (MINLP) problems that combine the combinatorial difficulty of optimizing over discrete variable sets with the challenges of ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Transactions of The Japanese Society for Artificial Intelligence

سال: 2021

ISSN: ['1346-0714', '1346-8030']

DOI: https://doi.org/10.1527/tjsai.36-6_c-l44