paper-with-me

Papers

Boundary-Aware Uncertainty for Feature Attribution Explainers

2022-10-05 · Davin Hill, Aria Masoomi, Max Torop, Sandesh Ghimire, Jennifer Dy

Post-hoc explanation methods have become a critical tool for understanding black-box classifiers in high-stakes applications. However, high-performing classifiers are often highly nonlinear and can exhibit complex behavior around the decision boundary, leading to brittle or misleading local explanations. Therefore there is an impending need to quantify the uncertainty of such explanation methods in order to understand when explanations are trustworthy. In this work we propose the Gaussian Process Explanation UnCertainty (GPEC) framework, which generates a unified uncertainty estimate combining decision boundary-aware uncertainty with explanation function approximation uncertainty. We introduce a novel geodesic-based kernel, which captures the complexity of the target black-box decision boundary. We show theoretically that the proposed kernel similarity increases with decision boundary complexity. The proposed framework is highly flexible; it can be used with any black-box classifier and feature attribution method. Empirical results on multiple tabular and image datasets show that the GPEC uncertainty estimate improves understanding of explanations as compared to existing methods.

📄 PDF Abstract BibTeX arXiv:2210.02419

Code (1)

davinhill/gpec 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification

2026-05-20 · Yinsong Chen, Samson S. Yu, Zhong Li, Chee Peng Lim arxiv

Post-hoc explainable AI (XAI) methods usually return one attribution map, even when the model represents uncertainty in its parameters. We define the \emph{explanation distribution} as the distribution of attribution map…

Efficient Explanations from Empirical Explainers

2021-03-29 · EMNLP (BlackboxNLP) 2021 11 · Robert Schwarzenberg, Nils Feldhus, Sebastian Möller

Amid a discussion about Green AI in which we see explainability neglected, we explore the possibility to efficiently approximate computationally expensive explainers. To this end, we propose feature attribution modelling…

Selective Explanations

2024-05-29 · Lucas Monteiro Paes, Dennis Wei, Flavio P. Calmon

Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, …

Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective

2023-03-23 · Avi Schwarzschild, Max Cembalest, Karthik Rao, Keegan Hines 외

As neural networks increasingly make critical decisions in high-stakes settings, monitoring and explaining their behavior in an understandable and trustworthy manner is a necessity. One commonly used type of explainer is…

Explaining Predictive Uncertainty by Exposing Second-Order Effects

2024-01-30 · Florian Bley, Sebastian Lapuschkin, Wojciech Samek, Grégoire Montavon

Explainable AI has brought transparency into complex ML blackboxes, enabling, in particular, to identify which features these models use for their predictions. So far, the question of explaining predictive uncertainty, i…