Scholarlink

<p>How can we efficiently determine meta-parameter values for deep learning-based time-series forecasting given a time-series dataset? This paper introduces <i>Xtune</i>, an efficient and novel meta-parameter tuning method for deep learning-based time-series forecasting, leveraging explainable AI techniques. In particular, this study focuses on optimizing the window size for time-series forecasting. <i>Xtune</i> determines the optimal meta-parameter value for these methods and can also be applied to tune the window size for anomaly detection methods that utilize deep learning-based time-series forecasting. Extensive experiments on real-world datasets and forecasting methods demonstrate that <i>Xtune</i> efficiently identifies the optimal meta-parameter value and consistently outperforms the existing methods in terms of execution speed.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An XAI-based meta-parameter tuning for time-series forecasting

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月11日

查看全文
  • Hiroyuki Nakagawa,
  • Shimon Sumita,
  • Ryuichi Iida,
  • Tatsuhiro Tsuchiya

摘要

How can we efficiently determine meta-parameter values for deep learning-based time-series forecasting given a time-series dataset? This paper introduces Xtune, an efficient and novel meta-parameter tuning method for deep learning-based time-series forecasting, leveraging explainable AI techniques. In particular, this study focuses on optimizing the window size for time-series forecasting. Xtune determines the optimal meta-parameter value for these methods and can also be applied to tune the window size for anomaly detection methods that utilize deep learning-based time-series forecasting. Extensive experiments on real-world datasets and forecasting methods demonstrate that Xtune efficiently identifies the optimal meta-parameter value and consistently outperforms the existing methods in terms of execution speed.