从Hawkes过程到注意力：事件序列的时间调节机制
From Hawkes Processes to Attention: Time-Modulated Mechanisms for Event Sequences
AI总结：
本文提出Hawkes注意力机制，通过可学习的类型特定神经核调节查询、键和值投影，统一事件时间和内容交互，提升事件序列建模性能。
摘要：
标记时间点过程（MTPPs）自然出现在医疗、社交、商业和金融领域。然而，现有基于Transformer的方法大多仅通过位置编码注入时间信息，依赖于共享或参数衰减结构，限制了它们捕捉异质性和类型特定时间效应的能力。受此启发，我们从多元Hawkes过程理论中推导出一种新的注意力运算符，称为Hawkes注意力，利用可学习的类型特定神经核调节查询、键和值投影，从而替代传统注意力中的相应部分。得益于这种设计，Hawkes注意力统一了事件时间和内容交互，从数据中学习时间相关行为和类型特定激发模式。实验结果表明，我们的方法在对比基线方法上取得了更好的性能。除了通用的MTPP之外，我们的注意力机制还可以轻松应用于特定的时间结构，如时间序列预测。
英文摘要：
Marked Temporal Point Processes (MTPPs) arise naturally in medical, social, commercial, and financial domains. However, existing Transformer-based methods mostly inject temporal information only via positional encodings, relying on shared or parametric decay structures, which limits their ability to capture heterogeneous and type-specific temporal effects. Inspired by this observation, we derive a novel attention operator called Hawkes Attention from the multivariate Hawkes process theory for MTPP, using learnable per-type neural kernels to modulate query, key and value projections, thereby replacing the corresponding parts in the traditional attention. Benefited from the design, Hawkes Attention unifies event timing and content interaction, learning both the time-relevant behavior and type-specific excitation patterns from the data. The experimental results show that our method achieves better performance compared to the baselines. In addition to the general MTPP, our attention mechanism can also be easily applied to specific temporal structures, such as time series forecasting.
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。
