直接建模每步概率分布，提升时间序列预测的不确定性捕捉能力
Time Series Forecasting via Direct Per-Step Probability Distribution Modeling
- 用离散概率分布替代标量输出，每步预测更完整
- 在多个真实数据集上优于现有方法，长期趋势预测更稳定
- 双分支结构自监督约束，有效减少异常预测
基于深度神经网络的时间序列预测模型近年来在捕捉复杂时序依赖方面表现出色。然而，这些模型直接输出每个时间步的标量值，难以量化预测不确定性。为此，我们提出一种名为交错双分支概率分布网络（interPDN）的新模型，直接构建每步的离散概率分布，而非标量输出。每个时间步的回归结果通过在预定义支撑集上计算预测分布的期望获得。为缓解预测异常，引入双分支架构，采用交错支撑集，并加入粗粒度时间尺度分支以增强长期趋势预测能力。另一分支的输出作为辅助信号，对当前分支的预测施加自监督一致性约束。在多个真实世界数据集上的大量实验表明，interPDN表现显著优于现有方法。
原文摘要 · Abstract (English)
Deep neural network-based time series prediction models have recently demonstrated superior capabilities in capturing complex temporal dependencies. However, it is challenging for these models to account for uncertainty associated with their predictions, because they directly output scalar values at each time step. To address such a challenge, we propose a novel model named interleaved dual-branch Probability Distribution Network (interPDN), which directly constructs discrete probability distributions per step instead of a scalar. The regression output at each time step is derived by computing the expectation of the predictive distribution on a predefined support set. To mitigate prediction anomalies, a dual-branch architecture is introduced with interleaved support sets, augmented by coarse temporal-scale branches for long-term trend forecasting. Outputs from another branch are treated as auxiliary signals to impose self-supervised consistency constraints on the current branch's prediction. Extensive experiments on multiple real-world datasets demonstrate the superior performance of interPDN.
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。