用连续动态模型捕捉时间序列中的物理原型，提前发现链路故障。
Hierarchical ODE: Learning Continuous-Time Physical Prototypes for Early Link Failure Detection
- 基于神经微分方程构建连续时间原型，分离噪声与真实趋势。
- 自适应层级结构自动确定原型数量，无需预设类别数。
- 适用于不规则采样数据，适合早期故障检测场景。
时间序列原型学习面临观测模糊性的根本挑战。离散架构难以解决此问题，因其无法将随机噪声与连续动态解耦。此外，严格的闭集假设无法捕捉未见多样性。为此，我们提出一种分层常微分方程聚类网络，利用神经常微分方程建模潜在状态演化为连续积分曲线。该形式强制时间连续性，有效分离平滑特征趋势与随机噪声；同时，自适应分层机制可自主确定原型数量，摆脱刚性先验约束。在不规则采样时间序列的早期链路故障检测任务中验证，该方法能有效提取底层物理原型，实现鲁棒故障检测。代码已开源：https://github.com/NJ-LNN/Hierarchical-ODE。
原文摘要 · Abstract (English)
Time series prototype learning is fundamentally challenged by observational ambiguity. Discrete architectures fail to resolve this, as they lack the capacity to decouple stochastic noise from continuous dynamics. Furthermore, rigid closed-set assumptions fail to capture unseen diversity. To address these limitations, we propose a hierarchical ordinary differential equation clustering network, which utilizes neural ordinary differential equation to model latent state evolution as a continuous integral curve. This formulation enforces temporal continuity to effectively disentangle smooth feature trends from stochastic noise, while our adaptive hierarchical mechanism autonomously determines the appropriate number of prototypes without rigid prior constraints. Validated on the early link failure detection task with irregularly sampled time series, the proposed method effectively extracts underlying physical prototypes, thereby enabling robust failure detection. Our code is available at https://github.com/NJ-LNN/Hierarchical-ODE.
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。