paper-with-me

Papers

Time Series Model Attribution Visualizations as Explanations

2021-09-27 · Udo Schlegel, Daniel A. Keim

Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attributions for samples, for instance, on images. However, heatmaps are not always the ideal visualization to explain certain model decisions for other data types. In this review, we focus on attribution visualizations for time series. We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.

📄 PDF Abstract BibTeX arXiv:2109.12935

Code (0)

등록된 구현이 없습니다.

Tasks

modelPositionTime SeriesTime Series Analysis

Methods 이 논문이 사용한 방법론

Heatmap 설명 없음

Similar Papers 제목 키워드 기반

Interactive dense pixel visualizations for time series and model attribution explanations

2024-08-27 · Udo Schlegel, Daniel A. Keim

The field of Explainable Artificial Intelligence (XAI) for Deep Neural Network models has developed significantly, offering numerous techniques to extract explanations from models. However, evaluating explanations is oft…

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Time Series

Towards A Unified Information Bottleneck Framework for Time Series Explanations

2026-08-26 · Xu Zheng, Zichuan Liu, Zhuomin Chen, Mayur Akewar 외 arxiv

Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into …

Visual Explanations with Attributions and Counterfactuals on Time Series Classification

2023-07-14 · Udo Schlegel, Daniela Oelke, Daniel A. Keim, Mennatallah El-Assady

With the rising necessity of explainable artificial intelligence (XAI), we see an increase in task-dependent XAI methods on varying abstraction levels. XAI techniques on a global level explain model behavior and on a loc…

Decision MakingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)Time Series+1

Introducing the Attribution Stability Indicator: a Measure for Time Series XAI Attributions

2023-10-06 · Udo Schlegel, Daniel A. Keim

Given the increasing amount and general complexity of time series data in domains such as finance, weather forecasting, and healthcare, there is a growing need for state-of-the-art performance models that can provide int…

Time SeriesTime Series ClassificationWeather Forecasting

How does this interaction affect me? Interpretable attribution for feature interactions

2020-06-19 · NeurIPS 2020 12 · Michael Tsang, Sirisha Rambhatla, Yan Liu

Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextu…