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 2502.09341cs.LGcs.AI
收藏

神经时空点过程:趋势与挑战

Neural Spatiotemporal Point Processes: Trends and Challenges

German Research Center for Artificial Intelligence(德国人工智能研究中心);Boston College(波士顿学院);University of Kaiserslautern–Landau(凯泽斯劳滕-兰道大学);Mohammed VI Polytechnic University(穆罕默德六世理工大学);Georgia Institute of Technology(佐治亚理工学院)

Sumantrak Mukherjee, Mouad Elhamdi, George Mohler, David A. Selby, Yao Xie, Sebastian Vollmer, Gerrit Grossmann

AI总结:

本综述围绕神经时空点过程展开,分析其结合深度学习应对复杂事件数据的优势,对现有方法分类、统一设计选择,阐述挑战、新兴趋势及应用,并指出文献空白。

摘要:

时空点过程(STPPs)是用于连续时空事件的概率模型。现实世界事件数据常呈现复杂依赖关系与异质动态。通过结合现代深度学习技术,STPPs能比传统方法更有效建模这些复杂性。因此,神经方法与STPPs的融合已成为活跃且快速发展的研究领域。本综述对现有方法分类,统一关键设计选择,解释该数据模态的挑战,进一步强调新兴趋势与多样应用领域,最后指出文献中的开放挑战与空白。

英文摘要:

Spatiotemporal point processes (STPPs) are probabilistic models for events occurring in continuous space and time. Real-world event data often exhibit intricate dependencies and heterogeneous dynamics. By incorporating modern deep learning techniques, STPPs can model these complexities more effectively than traditional approaches. Consequently, the fusion of neural methods with STPPs has become an active and rapidly evolving research area. In this review, we categorize existing approaches, unify key design choices, and explain the challenges of working with this data modality. We further highlight emerging trends and diverse application domains. Finally, we identify open challenges and gaps in the literature.

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。

↑