English
Related papers

Related papers: Considerations When Learning Additive Explanations…

200 papers

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…

Computation and Language · Computer Science 2024-03-19 Siwen Luo , Hamish Ivison , Caren Han , Josiah Poon

SHAP is a popular approach to explain black-box models by revealing the importance of individual features. As it ignores feature interactions, SHAP explanations can be confusing up to misleading. NSHAP, on the other hand, reports the…

Machine Learning · Computer Science 2024-04-22 Sascha Xu , Joscha Cüppers , Jilles Vreeken

Although counterfactual explanations are a popular approach to explain ML black-box classifiers, they are less widespread in NLP. Most methods find those explanations by iteratively perturbing the target document until it is classified…

Computation and Language · Computer Science 2024-04-24 Julien Delaunay , Luis Galárraga , Christine Largouët

In this paper, we address the "black-box" problem in predictive process analytics by building interpretable models that are capable to inform both what and why is a prediction. Predictive process analytics is a newly emerged discipline…

Machine Learning · Computer Science 2022-04-26 Bemali Wickramanayake , Zhipeng He , Chun Ouyang , Catarina Moreira , Yue Xu , Renuka Sindhgatta

As Artificial Intelligence (AI) is having more influence on our everyday lives, it becomes important that AI-based decisions are transparent and explainable. As a consequence, the field of eXplainable AI (or XAI) has become popular in…

Artificial Intelligence · Computer Science 2024-04-18 Nils Ole Breuer , Andreas Sauter , Majid Mohammadi , Erman Acar

Interpretable representations are the backbone of many explainers that target black-box predictive systems based on artificial intelligence and machine learning algorithms. They translate the low-level data representation necessary for good…

Machine Learning · Computer Science 2024-04-29 Kacper Sokol , Peter Flach

The importance of explainability in AI has become a pressing concern, for which several explainable AI (XAI) approaches have been recently proposed. However, most of the available XAI techniques are post-hoc methods, which however may be…

Machine Learning · Computer Science 2022-04-15 Leonardo Lucio Custode , Giovanni Iacca

We study the faithfulness of an explanation system to the underlying prediction model. We show that this can be captured by two properties, consistency and sufficiency, and introduce quantitative measures of the extent to which these hold.…

Machine Learning · Computer Science 2022-02-03 Sanjoy Dasgupta , Nave Frost , Michal Moshkovitz

There has been a recent push in making machine learning models more interpretable so that their performance can be trusted. Although successful, these methods have mostly focused on the deep learning methods while the fundamental…

Machine Learning · Computer Science 2022-06-16 David Steinmann , Matej Zečević , Devendra Singh Dhami , Kristian Kersting

We interpret the predictions of any black-box structured input-structured output model around a specific input-output pair. Our method returns an "explanation" consisting of groups of input-output tokens that are causally related. These…

Machine Learning · Computer Science 2017-11-16 David Alvarez-Melis , Tommi S. Jaakkola

Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another. We describe a new unified class of methods, removal-based…

Machine Learning · Computer Science 2022-05-16 Ian Covert , Scott Lundberg , Su-In Lee

Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test. Recent work on…

Machine Learning · Computer Science 2017-11-15 Andrew Slavin Ross , Michael C. Hughes , Finale Doshi-Velez

The popular generalized additive model framework is extended to allow both the mean curves and the response distribution to be nonparametric. The approach is demonstrated to be a flexible yet parsimonious tool for data analysis in its own…

Methodology · Statistics 2017-09-18 Alan Huang , Nanxi Zhang

Model-agnostic feature attributions can provide local insights in complex ML models. If the explanation is correct, a domain expert can validate and trust the model's decision. However, if it contradicts the expert's knowledge, related work…

Machine Learning · Computer Science 2023-06-30 Joran Michiels , Maarten De Vos , Johan Suykens

This study explores the impact of class outliers on the effectiveness of example-based explainability methods for black-box machine learning models. We reformulate existing explainability evaluation metrics, such as correctness and…

Machine Learning · Computer Science 2024-08-02 Ikhtiyor Nematov , Dimitris Sacharidis , Tomer Sagi , Katja Hose

To this day, a variety of approaches for providing local interpretability of black-box machine learning models have been introduced. Unfortunately, all of these methods suffer from one or more of the following deficiencies: They are either…

Machine Learning · Computer Science 2022-03-08 Yiran Huang , Nicole Schaal , Michael Hefenbrock , Yexu Zhou , Till Riedel , Likun Fang , Michael Beigl

We provide a flexible framework for selecting among a class of additive partial linear models that allows both linear and nonlinear additive components. In practice, it is challenging to determine which additive components should be…

Methodology · Statistics 2021-09-20 Seonghyun Jeong , Taeyoung Park , David A. van Dyk

We introduce Matched Machine Learning, a framework that combines the flexibility of machine learning black boxes with the interpretability of matching, a longstanding tool in observational causal inference. Interpretability is paramount in…

Methodology · Statistics 2023-04-05 Marco Morucci , Cynthia Rudin , Alexander Volfovsky

We investigate whether three types of post hoc model explanations--feature attribution, concept activation, and training point ranking--are effective for detecting a model's reliance on spurious signals in the training data. Specifically,…

Machine Learning · Computer Science 2022-12-12 Julius Adebayo , Michael Muelly , Hal Abelson , Been Kim

Generalized additive models (GAMs) are favored in many regression and binary classification problems because they are able to fit complex, nonlinear functions while still remaining interpretable. In the first part of this paper, we…

Machine Learning · Computer Science 2019-06-03 Xuezhou Zhang , Sarah Tan , Paul Koch , Yin Lou , Urszula Chajewska , Rich Caruana
‹ Prev 1 8 9 10 Next ›