中文
相关论文

相关论文: Global Counterfactual Explanations: Investigations…

200 篇论文

Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions. For CEs to be useful, it is important that they are easy for users to interpret. Existing methods for…

机器学习 · 计算机科学 2021-03-17 Lisa Schut , Oscar Key , Rory McGrath , Luca Costabello , Bogdan Sacaleanu , Medb Corcoran , Yarin Gal

When applicants get rejected by an algorithmic decision system, recourse explanations provide actionable suggestions for how to change their input features to get a positive evaluation. A crucial yet overlooked phenomenon is that recourse…

Counterfactual explanations (CFEs) provide actionable recourse, but most methods assume a static framework with fixed data and a trained classifier. This assumption breaks in evolving data environments, such as data streams, where online…

机器学习 · 计算机科学 2026-05-19 Marcin Kostrzewa , Jerzy Stefanowski , Maciej Zięba

Due to the increasing use of machine learning in practice it becomes more and more important to be able to explain the prediction and behavior of machine learning models. An instance of explanations are counterfactual explanations which…

机器学习 · 计算机科学 2019-11-19 André Artelt , Barbara Hammer

Counterfactual explanations are a widely used approach in Explainable AI, offering actionable insights into decision-making by illustrating how small changes to input data can lead to different outcomes. Despite their importance, evaluating…

人机交互 · 计算机科学 2025-04-22 Marharyta Domnich , Rasmus Moorits Veski , Julius Välja , Kadi Tulver , Raul Vicente

Explainable artificial intelligence (XAI) has become increasingly important in decision-critical domains such as healthcare, finance, and law. Counterfactual (CF) explanations, a key approach in XAI, provide users with actionable insights…

人工智能 · 计算机科学 2025-07-22 Volkan Bakir , Polat Goktas , Sureyya Akyuz

Counterfactual explanations are a prominent example of post-hoc interpretability methods in the explainable Artificial Intelligence research domain. They provide individuals with alternative scenarios and a set of recommendations to achieve…

人工智能 · 计算机科学 2021-01-20 Andrea Ferrario , Michele Loi

Counterfactual explanations are a popular type of explanation for making the outcomes of a decision making system transparent to the user. Counterfactual explanations tell the user what to do in order to change the outcome of the system in…

机器学习 · 计算机科学 2022-11-29 André Artelt , Barbara Hammer

Interpretability research takes counterfactual theories of causality for granted. Most causal methods rely on counterfactual interventions to inputs or the activations of particular model components, followed by observations of the change…

机器学习 · 计算机科学 2024-07-08 Aaron Mueller

AI-driven outcomes can be challenging for end-users to understand. Explanations can address two key questions: "Why this outcome?" (factual) and "Why not another?" (counterfactual). While substantial efforts have been made to formalize…

人工智能 · 计算机科学 2025-03-21 Suryani Lim , Henri Prade , Gilles Richard

Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model's behavior, they hint users towards possible actions and give grounds…

Counterfactual Explanations (CEs) are an important tool in Algorithmic Recourse for addressing two questions: 1. What are the crucial factors that led to an automated prediction/decision? 2. How can these factors be changed to achieve a…

机器学习 · 计算机科学 2023-11-23 Xuan Zhao , Klaus Broelemann , Gjergji Kasneci

Recently, a groundswell of research has identified the use of counterfactual explanations as a potentially significant solution to the Explainable AI (XAI) problem. It is argued that (a) technically, these counterfactual cases can be…

人工智能 · 计算机科学 2020-05-29 Mark T. Keane , Barry Smyth

With the ongoing rise of machine learning, the need for methods for explaining decisions made by artificial intelligence systems is becoming a more and more important topic. Especially for image classification tasks, many state-of-the-art…

机器学习 · 计算机科学 2022-05-10 Silvan Mertes , Tobias Huber , Katharina Weitz , Alexander Heimerl , Elisabeth André

Counterfactual explanations emerge as a powerful approach in explainable AI, providing what-if scenarios that reveal how minimal changes to an input time series can alter the model's prediction. This work presents a survey of recent…

机器学习 · 计算机科学 2026-03-31 Udo Schlegel , Thomas Seidl

Reinforcement Learning (RL) has shown great promise in domains like healthcare and robotics but often struggles with adoption due to its lack of interpretability. Counterfactual explanations, which address "what if" scenarios, provide a…

机器学习 · 计算机科学 2025-05-20 Shuyang Dong , Shangtong Zhang , Lu Feng

Counterfactual explanations are usually obtained by identifying the smallest change made to an input to change a prediction made by a fixed model (hereafter called sparse methods). Recent work, however, has revitalized an old insight: there…

机器学习 · 计算机科学 2020-06-24 Martin Pawelczyk , Klaus Broelemann , Gjergji Kasneci

Recent work on counterfactual visual explanations has contributed to making artificial intelligence models more explainable by providing visual perturbation to flip the prediction. However, these approaches neglect the causal relationships…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Yiran Qiao , Disheng Liu , Yiren Lu , Yu Yin , Mengnan Du , Jing Ma

Counterfactual Explanations (CE) face several unresolved challenges, such as ensuring stability, synthesizing multiple CEs, and providing plausibility and sparsity guarantees. From a more practical point of view, recent studies [Pawelczyk…

机器学习 · 统计学 2024-03-19 Salim I. Amoukou , Nicolas J. B Brunel

Modern recommender systems face an increasing need to explain their recommendations. Despite considerable progress in this area, evaluating the quality of explanations remains a significant challenge for researchers and practitioners. Prior…

人工智能 · 计算机科学 2022-11-18 Yuanshun Yao , Chong Wang , Hang Li