arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.07189cs.LG
收藏

连续时间序列的学习神经模型

Learning Neural Models for Continuous-Time Sequences

IIT Delhi(印度理工学院德里分校)

Vinayak Gupta

摘要:

由人类活动产生的大量数据,如在线购买,健康记录,空间移动等,被存储为连续时间内的事件序列。在这样的序列上学习深度学习方法是一项重要的任务,因为它涉及对不断增加的事件时间戳、事件间时间间隔、事件类型以及事件之间的影响进行建模-在不同序列内和跨不同序列。这种情况进一步加剧了与数据汇集,例如有限的数据,不完整的序列,隐私限制等的研究方向在这项工作中所描述的约束,我们的目标是研究连续时间事件序列(CTES)的属性和设计强大的但可扩展的神经网络为基础的模型,以克服上述问题。在这项工作中,我们使用标记的时间点过程(MTPP),以解决广泛的现实世界中的问题的事件的底层生成分布模型。此外,我们强调了所提出的方法在最先进的基线上的有效性,并随后报告了正在进行的研究问题。

英文摘要:

The large volumes of data generated by human activities such as online purchases, health records, spatial mobility etc. are stored as a sequence of events over a continuous time. Learning deep learning methods over such sequences is a non-trivial task as it involves modeling the ever-increasing event timestamps, inter-event time gaps, event types, and the influences between events -- within and across different sequences. This situation is further exacerbated by the constraints associated with data collection e.g. limited data, incomplete sequences, privacy restrictions etc. With the research direction described in this work, we aim to study the properties of continuous-time event sequences (CTES) and design robust yet scalable neural network-based models to overcome the aforementioned problems. In this work, we model the underlying generative distribution of events using marked temporal point processes (MTPP) to address a wide range of real-world problems. Moreover, we highlight the efficacy of the proposed approaches over the state-of-the-art baselines and later report the ongoing research problems.

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。

↑