融合静态与动态特征，提升时间序列预测的可解释性与鲁棒性。
Robust Multi-Modal Forecasting: Integrating Static and Dynamic Features
- 通过分解外生时间序列为趋势与属性，构建可解释编码机制。
- 在多个合成数据集上保持高预测精度与稳定解释性。
- 适合医疗等需透明决策的高风险场景使用。
时间序列预测在医疗等领域至关重要，准确预测未来健康轨迹可显著影响临床决策。确保模型的透明性与可解释性对关键场景的采纳至关重要。现有研究采用自上而下的双层透明框架，聚焦于利用静态特征理解预测序列的趋势与属性。本文扩展该框架，以结构化方式整合外生时间序列特征与静态特征，同时保持整体可解释性。方法基于轨迹理解的洞察，引入外生时间序列的编码机制，将其分解为有意义的趋势与属性，从而提取可解释模式。在多个合成数据集上的实验表明，该方法在保持预测性能的同时，具备良好的可解释性与鲁棒性。本工作推动了鲁棒、泛化性强的时间序列预测模型的发展。代码已公开于 https://github.com/jeremy-qin/TIMEVIEW。
原文摘要 · Abstract (English)
Time series forecasting plays a crucial role in various applications, particularly in healthcare, where accurate predictions of future health trajectories can significantly impact clinical decision-making. Ensuring transparency and explainability of the models responsible for these tasks is essential for their adoption in critical settings. Recent work has explored a top-down approach to bi-level transparency, focusing on understanding trends and properties of predicted time series using static features. In this work, we extend this framework by incorporating exogenous time series features alongside static features in a structured manner, while maintaining cohesive interpretation. Our approach leverages the insights of trajectory comprehension to introduce an encoding mechanism for exogenous time series, where they are decomposed into meaningful trends and properties, enabling the extraction of interpretable patterns. Through experiments on several synthetic datasets, we demonstrate that our approach remains predictive while preserving interpretability and robustness. This work represents a step towards developing robust, and generalized time series forecasting models. The code is available at https://github.com/jeremy-qin/TIMEVIEW
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。