paper-with-me

홈 › Papers

A Deep Dive into Perturbations as Evaluation Technique for Time Series XAI

2023-07-11 · Udo Schlegel, Daniel A. Keim

Explainable Artificial Intelligence (XAI) has gained significant attention recently as the demand for transparency and interpretability of machine learning models has increased. In particular, XAI for time series data has become increasingly important in finance, healthcare, and climate science. However, evaluating the quality of explanations, such as attributions provided by XAI techniques, remains challenging. This paper provides an in-depth analysis of using perturbations to evaluate attributions extracted from time series models. A perturbation analysis involves systematically modifying the input data and evaluating the impact on the attributions generated by the XAI method. We apply this approach to several state-of-the-art XAI techniques and evaluate their performance on three time series classification datasets. Our results demonstrate that the perturbation analysis approach can effectively evaluate the quality of attributions and provide insights into the strengths and limitations of XAI techniques. Such an approach can guide the selection of XAI methods for time series data, e.g., focusing on return time rather than precision, and facilitate the development of more reliable and interpretable machine learning models for time series analysis.

📄 PDF Abstract BibTeX arXiv:2307.05104

Code (1)

visual-xai-for-time-series/time-series-xai-perturbation-analysis 공식 구현 pytorch

Tasks

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)Interpretable Machine LearningTime SeriesTime Series AnalysisTime Series Classification

Similar Papers 제목 키워드 기반

Retrieval-guided Counterfactual Generation for QA

2021-10-14 · ACL 2022 5 · Bhargavi Paranjape, Matthew Lamm, Ian Tenney

Deep NLP models have been shown to learn spurious correlations, leaving them brittle to input perturbations. Recent work has shown that counterfactual or contrastive data -- i.e. minimally perturbed inputs -- can reveal …

counterfactualData AugmentationDiversityQuestion Answering+5

Diversified Sampling Improves Scaling LLM inference

2025-02-16 · Tianchun Wang, Zichuan Liu, Yuanzhou Chen, Jonathan Light 외

While increasing training compute has significantly improved the performance of large language models (LLMs), similar gains have not been observed when scaling inference compute. We hypothesize that the primary issue lie…

Code GenerationDiversity

Retrieval-guided Counterfactual Generation for QA

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Deep NLP models have been shown to be brittle to input perturbations. Recent work has shown that data augmentation using counterfactuals --- i.e. minimally perturbed inputs --- can help ameliorate this weakness. We focus…

counterfactualData AugmentationDiversityQuestion Answering+5

Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks

2022-08-11 · Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Neverthele…

Diversity

NAG: Network for Adversary Generation

2017-12-09 · CVPR 2018 6 · Konda Reddy Mopuri, Utkarsh Ojha, Utsav Garg, R. Venkatesh Babu

Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing m…