提出可解释的时间序列模型GATSM，兼顾透明性与预测性能。
Transparent Networks for Multivariate Time Series
- 分两部分：独立特征网络+可解释时序模块，保持透明性。
- 在多个数据集上超越传统可解释模型，接近黑箱模型表现。
- 适合需要可解释性的高风险场景，如医疗、金融时间序列分析。
透明模型因其可解释性在高风险领域备受关注。然而，尽管现实世界数据多为时间序列，针对透明时间序列模型的研究仍显不足。为此，我们提出一种新型透明神经网络模型——广义加性时间序列模型（GATSM）。GATSM由两部分构成：1）独立特征网络，用于学习特征表示；2）可解释的时序模块，利用特征表示捕捉跨时间步的时序模式。该结构使GATSM能有效建模时序依赖，处理变长序列，同时保持透明性。实验表明，GATSM显著优于现有广义加性模型，并达到与循环神经网络和Transformer等黑箱模型相当的性能。此外，我们还展示了GATSM能发现时间序列中的有意义模式。
原文摘要 · Abstract (English)
Transparent models, which provide inherently interpretable predictions, are receiving significant attention in high-stakes domains. However, despite much real-world data being collected as time series, there is a lack of studies on transparent time series models. To address this gap, we propose a novel transparent neural network model for time series called Generalized Additive Time Series Model (GATSM). GATSM consists of two parts: 1) independent feature networks to learn feature representations, and 2) a transparent temporal module to learn temporal patterns across different time steps using the feature representations. This structure allows GATSM to effectively capture temporal patterns and handle varying-length time series while preserving transparency. Empirical experiments show that GATSM significantly outperforms existing generalized additive models and achieves comparable performance to black-box time series models, such as recurrent neural networks and Transformer. In addition, we demonstrate that GATSM finds interesting patterns in time series.
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。