HyperNSDE：联合静态与纵向临床数据生成的个性化神经SDE

1. 12:00
   arXiv · Statistics Machine Learning

   HyperNSDE：面向联合静态-纵向临床数据生成的个性化神经 SDE

   HyperNSDE 是一种连续时间生成模型，通过 hypernetwork 将潜在 Neural SDE 条件化于静态患者表征，使基线特征在不依赖轨迹编码器的情况下塑造轨迹演化。观测时间通过依赖潜在状态的强度过程联合建模，并采用确定性-随机路径分解与非对抗 signature-kernel 目标稳定训练。模拟与真实临床数据集实验显示观测时间保真度提升且性能具竞争力。

Current heat 9·Comparable peak 10（Oct 7）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.