NICE: an algorithm for nearest instance counterfactual explanations

نویسندگان

چکیده

In this paper we propose a new algorithm, named NICE, to generate counterfactual explanations for tabular data that specifically takes into account algorithmic requirements often emerge in real-life deployments: (1) the ability provide an explanation all predictions, (2) being able handle any classification model (also non-differentiable ones), (3) efficient run time, and (4) providing multiple with different characteristics. More specifically, our approach exploits information from nearest unlike neighbor speed up search process, by iteratively introducing feature values instance be explained. We four versions of one without optimization and, three which optimize following properties: sparsity, proximity or plausibility. An extensive empirical comparison on 40 datasets shows algorithm outperforms current state-of-the-art terms these criteria. Our analyses show trade-off between hand plausibility other methods offering users choice select types counterfactuals they prefer. open-source implementation NICE can found at https://github.com/ADMAntwerp/NICE.

برای دانلود رایگان 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

An efficient instance selection algorithm for k nearest neighbor regression

The k-Nearest Neighbor algorithm(kNN) is an algorithm that is very simple to understand for classification or regression. It is also a lazy algorithm that does not use the training data points to do any generalization, in other words, it keeps all the training data during the testing phase. Thus, the population size becomes a major concern for kNN, since large population size may result in slow...

متن کامل

Nearest-Instance-Centroid-Estimation Linear Discriminant Analysis (NICE LDA)

We propose a novel ensemble classification technique called the Nearest Instance Centroid Estimation (NICE) LDA algorithm. Our algorithm (inspired from NICE KLMS) performs a combination of two weak classifiers threshold based clustering and linear discriminant classification to achieve stateof-the-art results on various high dimensional UCI datasets. We discuss the important ways in which our m...

متن کامل

Explanations of Counterfactual Inferences

When engaging in counterfactual thought, people must imagine changes to the actual state of the world. In this study, we investigated how people reason about counterfactual scenarios by asking participants to make counterfactual inferences about a series of causal devices (i.e., answer questions such as If component X had not operated [had failed], would components Y, Z, and W have operated?) a...

متن کامل

An Algorithm for Predicting Recurrence of Breast Cancer Using Genetic Algorithm and Nearest Neighbor Algorithm

Introduction: Breast cancer is one of the most common types of cancer and the most common type of malignancy in women, which has been growing in recent years. Patients with this disease have a chance of recurrence. Many factors reduce or increase this probability. Data mining is one of the methods used to detect or anticipate cancers, and one of its most common uses is to predict the recurrence...

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: Data Mining and Knowledge Discovery

سال: 2023

ISSN: ['1573-756X', '1384-5810']

DOI: https://doi.org/10.1007/s10618-023-00930-y