时间序列分类中可解释人工智能的软件框架：系统综述
Software Frameworks for Explainable AI in Time Series Classification: A Systematic Review
浏览论文内容
中文总结 AI 辅助
本研究为时间序列分类的可解释AI软件框架开展系统综述，对比多维度分析6个框架的局限性，提出需开发统一的时间序列专用可解释AI框架。
中文摘要 AI 辅助
时间序列出现在众多应用领域，并在决策关键场景中通过机器学习进行分析。时间序列分类（TSC）是研究最广泛且最具相关性的任务之一。在此背景下，确保TSC模型的透明性与可信赖性已成为重要需求，推动了可解释人工智能（XAI）方法的应用。尽管相关兴趣日益增长，但针对TSC的XAI研究仍较为零散，目前仍缺乏对现有解释生成软件框架、其评估实践及实际局限性的系统性理解。过往工作主要聚焦于单个解释方法，而跨框架一致性、时间序列特定评估及可复现性却鲜少受到关注。本综述中，我们分析了TSC领域现有用于解释生成与评估的软件框架，从支持的XAI方法、评估指标、可用性、基准支持及可复现性等多个维度对其进行比较，提供了首个针对时间序列的框架专项综述，包含实现比较及频域支持分析。我们识别出6个明确支持时间序列的框架，并揭示了共同局限性：尽管频域解释具有相关性，但仅1种方法支持；仅2种评估指标是专门为时间序列开发的；相同的XAI方法在不同框架中可产生差异显著的解释。基于这些发现，我们探讨了开放挑战并概述了未来研究方向，强调需开发统一的、时间序列专用的XAI框架，以实现忠实、可复现且感知时间序列的解释。
英文摘要
Time series arise in a wide range of application domains and are analyzed using machine learning in decision-critical settings. Time series classification (TSC) is one of the most widely studied and relevant tasks. In this context, ensuring the transparency and trustworthiness of TSC models has become an important requirement, motivating the use of explainable artificial intelligence (XAI) methods. Despite growing interest, research on XAI for TSC remains fragmented, and a systematic understanding of the available software frameworks for explanation generation, their evaluation practices, and practical limitations is still lacking. Prior work largely focused on individual explanation methods, while cross-framework consistency, time-series-specific evaluation, and reproducibility have received little attention. In this survey, we analyze existing software frameworks for explanation generation and evaluation in TSC. We compare them along multiple dimensions, including supported XAI methods, evaluation metrics, usability, benchmarking support, and reproducibility, providing the first time-series-specific survey of frameworks with implementation comparisons and an analysis of frequency-domain support. We identify six frameworks that explicitly support time series and reveal common limitations: only one method supports frequency-domain explanations despite their relevance; only two evaluation metrics have been developed specifically for time series; and identical XAI methods can yield substantially different explanations across frameworks. Based on these findings, we discuss open challenges and outline directions for future research, highlighting the need for unified, time-series-specific XAI frameworks that enable faithful, reproducible, and time-series-aware explanations.
发表机构
- Technische Hochschule Mittelhessen - University of Applied Science（中黑森应用技术大学）
- Hessian Center for AI (hessian.AI)（黑森人工智能中心）
- Marburg University（马尔堡大学）
机构由 AI 辅助整理，请以论文原文为准。
