paper-with-me

홈 › Papers

Ensured: Explanations for Decreasing the Epistemic Uncertainty in Predictions

2024-10-07 · Helena Löfström, Tuwe Löfström, Johan Hallberg Szabadvary

This paper addresses a significant gap in explainable AI: the necessity of interpreting epistemic uncertainty in model explanations. Although current methods mainly focus on explaining predictions, with some including uncertainty, they fail to provide guidance on how to reduce the inherent uncertainty in these predictions. To overcome this challenge, we introduce new types of explanations that specifically target epistemic uncertainty. These include ensured explanations, which highlight feature modifications that can reduce uncertainty, and categorisation of uncertain explanations counter-potential, semi-potential, and super-potential which explore alternative scenarios. Our work emphasises that epistemic uncertainty adds a crucial dimension to explanation quality, demanding evaluation based not only on prediction probability but also on uncertainty reduction. We introduce a new metric, ensured ranking, designed to help users identify the most reliable explanations by balancing trade-offs between uncertainty, probability, and competing alternative explanations. Furthermore, we extend the Calibrated Explanations method, incorporating tools that visualise how changes in feature values impact epistemic uncertainty. This enhancement provides deeper insights into model behaviour, promoting increased interpretability and appropriate trust in scenarios involving uncertain predictions.

📄 PDF Abstract BibTeX arXiv:2410.05479

Code (1)

moffran/calibrated_explanations 공식 구현

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Uncertainty Gating for Cost-Aware Explainable Artificial Intelligence

2026-03-31 · Georgii Mikriukov, Grégoire Montavon, Marina M. -C. Höhne arxiv

Post-hoc explanation methods are widely used to interpret black-box predictions, but their generation is often computationally expensive and their reliability is not guaranteed. We propose epistemic uncertainty as a low-…

Explanation GenerationImage Classification

Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AI

2025-07-17 · Chenrui Zhu, Louenas Bounia, Vu Linh Nguyen, Sébastien Destercke 외 arxiv

Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose…

The Impact of Machine Learning Uncertainty on the Robustness of Counterfactual Explanations

2026-01-20 · Leonidas Christodoulou, Chang Sun arxiv

Counterfactual explanations are widely used to interpret machine learning predictions by identifying minimal changes to input features that would alter a model's decision. However, most existing counterfactual methods ha…

VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability

2024-06-01 · Mohit Prabhushankar, Ghassan AlRegib

In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variability in the network predictions under pe…

Uncertainty Visualization

UbiQVision: Quantifying Uncertainty in XAI for Image Recognition

2025-12-23 · Akshat Dubey, Aleksandar Anžel, Bahar İlgen, Georges Hattab arxiv

Recent advances in deep learning have led to its widespread adoption across diverse domains, including medical imaging. This progress is driven by increasingly sophisticated model architectures, such as ResNets, Vision T…