paper-with-me

홈 › Papers

Observation-specific explanations through scattered data approximation

2024-04-12 · Valentina Ghidini, Michael Multerer, Jacopo Quizi, Rohan Sen

This work introduces the definition of observation-specific explanations to assign a score to each data point proportional to its importance in the definition of the prediction process. Such explanations involve the identification of the most influential observations for the black-box model of interest. The proposed method involves estimating these explanations by constructing a surrogate model through scattered data approximation utilizing the orthogonal matching pursuit algorithm. The proposed approach is validated on both simulated and real-world datasets.

📄 PDF Abstract BibTeX arXiv:2404.08747

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GrINd: Grid Interpolation Network for Scattered Observations

2024-03-28 · Andrzej Dulny, Paul Heinisch, Andreas Hotho, Anna Krause

Predicting the evolution of spatiotemporal physical systems from sparse and scattered observational data poses a significant challenge in various scientific domains. Traditional methods rely on dense grid-structured data…

Concept Activation Regions: A Generalized Framework For Concept-Based Explanations

2022-09-22 · Jonathan Crabbé, Mihaela van der Schaar

Concept-based explanations permit to understand the predictions of a deep neural network (DNN) through the lens of concepts specified by users. Existing methods assume that the examples illustrating a concept are mapped …

Feature Importance

A fast tunable blurring algorithm for scattered data

2019-06-16 · Gregor Robinson, Ian Grooms

A blurring algorithm with linear time complexity can reduce the small-scale content of data observed at scattered locations in a spatially extended domain of arbitrary dimension. The method works by forming a Gaussian in…

DeblurringState Estimation

A Hybrid Framework for Spatial Interpolation: Merging Data-driven with Domain Knowledge

2024-08-28 · Cong Zhang, Shuyi Du, Hongqing Song, Yuhe Wang

Estimating spatially distributed information through the interpolation of scattered observation datasets often overlooks the critical role of domain knowledge in understanding spatial dependencies. Additionally, the feat…

Spatial Interpolation

Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data

2026-07-02 · Emmanuel C. Chukwu, Rianne M. Schouten, Monique Tabak, Mykola Pechenizkiy arxiv

Counterfactual explanations (CEs) for multivariate time-series classifiers are often difficult to interpret in domains where experts reason in terms of semantic feature groups rather than individual channels. In rehabili…