连续时间事件数据的用户相关神经序列模型
User-Dependent Neural Sequence Models for Continuous-Time Event Data
摘要:
连续时间事件数据在个人行为数据、金融交易和医疗健康记录等应用中很常见。对这些数据进行建模可能非常具有挑战性,特别是对于具有许多不同类型事件的应用程序,因为它需要一个模型来预测事件类型以及发生时间。参数化时变强度函数的递归神经网络是当前使用此类数据进行预测建模的最新技术。这些模型通常假设所有事件序列都来自相同的数据分布。然而,在许多应用中,事件序列是由不同的源或用户生成的,并且它们的特征可能非常不同。在本文中,我们扩展了广泛的类神经标记点过程模型的混合物的潜在嵌入,其中每个混合物组件模型的特征特性的一个给定的用户。我们的方法依赖于增强这些模型与一个潜在的变量,编码用户的特征,表示通过摊销变分推断训练的用户行为的混合模型。我们在四个大型真实世界数据集上评估了我们的方法,并展示了我们的方法在各种预测指标(如对数似然,下一个事件排名和序列源识别)的现有工作中的系统改进。
英文摘要:
Continuous-time event data are common in applications such as individual behavior data, financial transactions, and medical health records. Modeling such data can be very challenging, in particular for applications with many different types of events, since it requires a model to predict the event types as well as the time of occurrence. Recurrent neural networks that parameterize time-varying intensity functions are the current state-of-the-art for predictive modeling with such data. These models typically assume that all event sequences come from the same data distribution. However, in many applications event sequences are generated by different sources, or users, and their characteristics can be very different. In this paper, we extend the broad class of neural marked point process models to mixtures of latent embeddings, where each mixture component models the characteristic traits of a given user. Our approach relies on augmenting these models with a latent variable that encodes user characteristics, represented by a mixture model over user behavior that is trained via amortized variational inference. We evaluate our methods on four large real-world datasets and demonstrate systematic improvements from our approach over existing work for a variety of predictive metrics such as log-likelihood, next event ranking, and source-of-sequence identification.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。