paper-with-me

Papers Counterfactual Explanation

“Counterfactual Explanation” 태그가 달린 논문 177편 · 필터 해제

Graph Style Transfer for Counterfactual Explainability

2025-05-23 · Bardh Prenkaj, Efstratios Zaradoukas, Gjergji Kasneci

Counterfactual explainability seeks to uncover model decisions by identifying minimal changes to the input that alter the predicted outcome. This task becomes particularly challenging for graph data due to preserving str…

counterfactualCounterfactual ExplanationGraph ClassificationStyle Transfer+1

COMRECGC: Global Graph Counterfactual Explainer through Common Recourse

2025-05-11 · Gregoire Fournier, Sourav Medya

Graph neural networks (GNNs) have been widely used in various domains such as social networks, molecular biology, or recommendation systems. Concurrently, different explanations methods of GNNs have arisen to complement …

Binary ClassificationcounterfactualCounterfactual ExplanationDrug Discovery+1

Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging

2025-04-11 · Gabriele Lozupone, Alessandro Bria, Francesco Fontanella, Frederick J. A. Meijer 외

This study presents Latent Diffusion Autoencoder (LDAE), a novel encoder-decoder diffusion-based framework for efficient and meaningful unsupervised learning in medical imaging, focusing on Alzheimer disease (AD) using b…

AttributeComputational EfficiencyCounterfactual ExplanationData Augmentation+9

Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection

2025-04-09 · Ruoyu Chen, Hua Zhang, Jingzhi Li, Li Liu 외

The objective of few-shot object detection (FSOD) is to detect novel objects with few training samples. The core challenge of this task is how to construct a generalized feature space for novel categories with limited da…

Contrastive LearningcounterfactualCounterfactual ExplanationFew-Shot Object Detection+2

Ranking Counterfactual Explanations

2025-03-20 · Suryani Lim, Henri Prade, Gilles Richard

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 ma…

counterfactualCounterfactual Explanation

Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures

2025-03-11 · Erfaun Noorani, Pasan Dissanayake, Faisal Hamman, Sanghamitra Dutta

Counterfactual explanations indicate the smallest change in input that can translate to a different outcome for a machine learning model. Counterfactuals have generated immense interest in high-stakes applications such a…

counterfactualCounterfactual Explanationvalid

Advancing climate model interpretability: Feature attribution for Arctic melt anomalies

2025-02-11 · Tolulope Ale, Nicole-Jeanne Schlegel, Vandana P. Janeja

The focus of our work is improving the interpretability of anomalies in climate models and advancing our understanding of Arctic melt dynamics. The Arctic and Antarctic ice sheets are experiencing rapid surface melting a…

Anomaly DetectioncounterfactualCounterfactual Explanation

A Novel Multi-Objective Evolutionary Algorithm for Counterfactual Generation

2025-02-03 · Gabriel Doyle-Finch, Alex A. Freitas

Machine learning algorithms that learn black-box predictive models (which cannot be directly interpreted) are increasingly used to make predictions affecting the lives of people. It is important that users understand the…

counterfactualCounterfactual Explanation

Leveraging counterfactual concepts for debugging and improving CNN model performance

2025-01-19 · SYED ALI TARIQ, Tehseen Zia

Counterfactual explanation methods have recently received significant attention for explaining CNN-based image classifiers due to their ability to provide easily understandable explanations that align more closely with h…

counterfactualCounterfactual ExplanationCounterfactual Reasoningimage-classification+1

Faithful Counterfactual Visual Explanations (FCVE)

2025-01-12 · Bismillah Khan, SYED ALI TARIQ, Tehseen Zia, Muhammad Ahsan 외

Deep learning models in computer vision have made remarkable progress, but their lack of transparency and interpretability remains a challenge. The development of explainable AI can enhance the understanding and performa…

counterfactualCounterfactual ExplanationDecision Making

Robust Counterfactual Explanations under Model Multiplicity Using Multi-Objective Optimization

2025-01-10 · Keita Kinjo

In recent years, explainability in machine learning has gained importance. In this context, counterfactual explanation (CE), which is an explanation method that uses examples, has attracted attention. However, it has bee…

counterfactualCounterfactual ExplanationDecision Making

Counterfactual Explanation for Auto-Encoder Based Time-Series Anomaly Detection

2025-01-03 · Abhishek Srinivasan, Varun Singapuri Ravi, Juan Carlos Andresen, Anders Holst

The complexity of modern electro-mechanical systems require the development of sophisticated diagnostic methods like anomaly detection capable of detecting deviations. Conventional anomaly detection approaches like signa…

Anomaly DetectioncounterfactualCounterfactual ExplanationDecision Making+3

Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition

2025-01-01 · CVPR 2025 1 · Lintong Zhang, Kang Yin, Seong-Whan Lee

Attribution-based explanation techniques capture key patterns to enhance visual interpretability. However, these patterns often lack the granularity needed for insight in fine-grained tasks, particularly in cases of …

counterfactualCounterfactual Explanation

Adopting Trustworthy AI for Sleep Disorder Prediction: Deep Time Series Analysis with Temporal Attention Mechanism and Counterfactual Explanations

2024-12-25 · Pegah Ahadian, Wei Xu, Sherry Wang, Qiang Guan

Sleep disorders have a major impact on both lifestyle and health. Effective sleep disorder prediction from lifestyle and physiological data can provide essential details for early intervention. This research utilizes thr…

counterfactualCounterfactual ExplanationTime SeriesTime Series Analysis

Multi-SpaCE: Multi-Objective Subsequence-based Sparse Counterfactual Explanations for Multivariate Time Series Classification

2024-12-14 · Mario Refoyo, David Luengo

Deep Learning systems excel in complex tasks but often lack transparency, limiting their use in critical applications. Counterfactual explanations, a core tool within eXplainable Artificial Intelligence (XAI), offer insi…

counterfactualCounterfactual ExplanationExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)+2

Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI

2024-11-22 · CVPR 2025 1 · Won Jun Kim, Hyungjin Chung, JaeMin Kim, Sangmin Lee 외

Gradient-based methods are a prototypical family of explainability techniques, especially for image-based models. Nonetheless, they have several shortcomings in that they (1) require white-box access to models, (2) are v…

counterfactualCounterfactual Explanation

Counterfactual Explanations via Riemannian Latent Space Traversal

2024-11-04 · Paraskevas Pegios, Aasa Feragen, Andreas Abildtrup Hansen, Georgios Arvanitidis

The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for providing actionable explanations to pra…

counterfactualCounterfactual ExplanationDecoder

M-CELS: Counterfactual Explanation for Multivariate Time Series Data Guided by Learned Saliency Maps

2024-11-04 · Peiyu Li, Omar Bahri, Soukaina Filali Boubrahimi, Shah Muhammad Hamdi

Over the past decade, multivariate time series classification has received great attention. Machine learning (ML) models for multivariate time series classification have made significant strides and achieved impressive s…

ClassificationcounterfactualCounterfactual ExplanationTime Series+1

A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers

2024-11-04 · Stephen McAleese, Mark Keane

Counterfactual explanations can be used to interpret and debug text classifiers by producing minimally altered text inputs that change a classifier's output. In this work, we evaluate five methods for generating counterf…

counterfactualCounterfactual Explanationvalid

Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments

2024-10-28 · Marharyta Domnich, Julius Valja, Rasmus Moorits Veski, Giacomo Magnifico 외

As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identify the minimal input changes needed to o…

counterfactualCounterfactual ExplanationDecision Making
1–20 / 177 다음 →