Continuously-observed event occurrences, often exhibit self- and mutually-exciting effects, which can be well modeled using temporal point processes. Beyond that, these event dynamics may also change over time, with certain periodic trends. We propose a novel variational auto-encoder to capture such a mixture of temporal dynamics. More specifically, the whole time interval of the input sequence is partitioned into a set of sub-intervals. The event dynamics are assumed to be stationary within each sub-interval, but could be changing across those sub-intervals. In particular, we use a sequential latent variable model to learn a dependency graph between the observed dimensions, for each sub-interval. The model predicts the future event times, by using the learned dependency graph to remove the noncontributing influences of past events. By doing so, the proposed model demonstrates its higher accuracy in predicting inter-event times and event types for several real-world event sequences, compared with existing state of the art neural point processes.

翻译：连续观测的事件发生往往表现出自激发和互激发效应，这类效应可通过时间点过程进行良好建模。此外，这些事件动态可能随时间变化并呈现周期性趋势。本文提出一种新颖的变分自编码器来捕捉这种混合时间动态。具体而言，输入序列的整个时间区间被划分为若干子区间。假设事件动态在每个子区间内保持平稳，但在不同子区间间可能发生变化。特别地，我们采用序贯潜变量模型为每个子区间学习观测维度间的依赖图。该模型通过利用学习到的依赖图消除过去事件中非贡献性影响，从而预测未来事件时间。通过这种方式，与现有最先进的神经点过程相比，所提模型在多个真实事件序列的预测中展现出更高的事件间隔时间与事件类型预测精度。