Learning Conditional Generative Models for Temporal Point Processes
Learning Conditional Generative Models for Temporal Point Processes
复制标题
DOI：
10.1609/aaai.v32i1.12072
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Shuai Xiao;Hongteng Xu;Junchi Yan;Mehrdad Farajtabar;Xiaokang Yang;Le Song;H. Zha
中科院分区：
文献类型：
--
作者：
Shuai Xiao;Hongteng Xu;Junchi Yan;Mehrdad Farajtabar;Xiaokang Yang;Le Song;H. Zha
在时间分析中，根据当前观测数据估计未来事件序列是一项长期而具有挑战性的任务。一方面，对于许多现实世界的问题，潜在的动力可能非常复杂，而且往往是未知的。这使得传统的参数点过程模型往往因其容量有限而不能很好地拟合数据。另一方面，长期预测存在偏差暴露的问题，即误差累积并传播到未来预测。我们的新模型建立在序列到序列(Seq2seq)预测网络的基础上。与参数点过程模型相比，它的建模能力更高，对真实数据的拟合具有更好的灵活性。本文的主要创新之处在于，除了传统SEQ2SEQ模型中使用的负最大似然损失外，通过引入基于点过程之间Wasserstein距离的无似然损失来缓解第二个挑战。与KL发散即最大似然估计损失不同，Wasserstein距离对样本之间的基本几何结构敏感，并能强健地强制样本之间紧密的几何结构。事实证明，这项技术能够在各种任务上显著改进Vanilla seq2seq模型。
Estimating the future event sequence conditioned on current observations is a long-standing and challenging task in temporal analysis. On one hand for many real-world problems the underlying dynamics can be very complex and often unknown. This renders the traditional parametric point process models often fail to fit the data for their limited capacity. On the other hand, long-term prediction suffers from the problem of bias exposure where the error accumulates and propagates to future prediction. Our new model builds upon the sequence to sequence (seq2seq) prediction network. Compared with parametric point process models, its modeling capacity is higher and has better flexibility for fitting real-world data. The main novelty of the paper is to mitigate the second challenge by introducing the likelihood-free loss based on Wasserstein distance between point processes, besides negative maximum likelihood loss used in the traditional seq2seq model. Wasserstein distance, unlike KL divergence i.e. MLE loss, is sensitive to the underlying geometry between samples and can robustly enforce close geometry structure between them. This technique is proven able to improve the vanilla seq2seq model by a notable margin on various tasks.