让时间序列模型的解释与人类认知对齐，提升可信度。
Interpretability in Deep Time Series Models Demands Semantic Alignment
- 强调模型解释需符合人类对时间现象的理解逻辑。
- 提出语义对齐需随时间演化保持稳定，区别于静态模型。
- 适合关注模型可信性与可解释性的研究人员。
深度时间序列模型的预测性能持续提升，但其部署受限于黑箱特性。现有可解释性方法仍聚焦于模型内部计算的解释，未考虑是否与人类对研究现象的推理方式对齐。本文主张，深度时间序列模型的可解释性应追求语义对齐：预测应以终端用户理解的变量表达，并通过时空机制实现，且能纳入用户相关的约束。我们形式化这一要求，指出一旦建立，语义对齐必须在时间演化中得以维持——这是静态场景中不存在的约束。基于此定义，我们提出语义对齐模型的设计蓝图，识别支持信任的关键属性，并讨论对模型设计的影响。
原文摘要 · Abstract (English)
Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal model computations, without addressing whether they align or not with how a human would reason about the studied phenomenon. Instead, we state interpretability in deep time series models should pursue semantic alignment: predictions should be expressed in terms of variables that are meaningful to the end user, mediated by spatial and temporal mechanisms that admit user-dependent constraints. In this paper, we formalize this requirement and state that, once established, semantic alignment must be preserved under temporal evolution: a constraint with no analog in static settings. Provided with this definition, we outline a blueprint for semantically aligned deep time series models, identify properties that support trust, and discuss implications for model design.
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。