提出可解释的时空预测模型FDN，兼顾精度与效率。
FDN: Interpretable Spatiotemporal Forecasting with Future Decomposition Networks
- 通过未来分解网络分离时序模式，实现可解释预测
- 在水文、交通、能源数据上精度接近最优方法
- 仅需少量内存和运行时间，适合实时应用
时空系统由空间分布但相互关联的实体组成，每个实体产生独特的动态信号。近年来虽出现诸多高性能预测方法，但大多缺乏可解释性。为此，我们提出未来分解网络（FDN），一种新型预测模型，能够：(a) 通过分类提供可解释的预测结果；(b) 揭示目标时间序列中的潜在活动模式；(c) 在远低于主流方法的内存与运行成本下，达到与最先进方法相当的预测性能。我们在水文、交通和能源系统的多个数据集上进行了全面分析，验证了其在准确率和可解释性方面的优势。
原文摘要 · Abstract (English)
Spatiotemporal systems comprise a collection of spatially distributed yet interdependent entities each generating unique dynamic signals. Highly sophisticated methods have been proposed in recent years delivering state-of-the-art (SOTA) forecasts but few have focused on interpretability. To address this, we propose the Future Decomposition Network (FDN), a novel forecast model capable of (a) providing interpretable predictions through classification (b) revealing latent activity patterns in the target time-series and (c) delivering forecasts competitive with SOTA methods at a fraction of their memory and runtime cost. We conduct comprehensive analyses on FDN for multiple datasets from hydrologic, traffic, and energy systems, demonstrating its improved accuracy and interpretability.
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。