提出解耦事件类型动态的新型点过程模型，提升预测精度与泛化能力。
ITPP: Learning Disentangled Event Dynamics in Marked Temporal Point Processes
- 采用基于ODE的编码器-解码器架构，分离不同事件类型的表示
- 在多个真实与合成数据集上，预测准确率优于现有最优模型
- 适合需要解析异构事件间动态关系的研究场景
标记时间点过程（MTPPs）通过依赖历史事件序列，为异步事件序列建模提供了严谨框架。然而，多数现有MTPP模型采用通道混杂策略，将不同事件类型信息编码到单一固定尺寸的潜在表征中，导致类型特异性动态被掩盖，进而降低性能并增加过拟合风险。本文提出ITPP，一种新型的通道独立型MTPP建模架构，通过基于常微分方程（ODE）的编码器-解码器框架实现事件类型信息的解耦。ITPP的核心是类型感知的反向自注意力机制，显式建模异质事件类型间的跨通道相关性。该架构在提升模型有效性与鲁棒性的同时，有效缓解过拟合问题。在多个真实世界与合成数据集上的全面实验表明，ITPP在预测准确率和泛化能力方面均持续优于当前最先进模型。
原文摘要 · Abstract (English)
Marked Temporal Point Processes (MTPPs) provide a principled framework for modeling asynchronous event sequences by conditioning on the history of past events. However, most existing MTPP models rely on channel-mixing strategies that encode information from different event types into a single, fixed-size latent representation. This entanglement can obscure type-specific dynamics, leading to performance degradation and increased risk of overfitting. In this work, we introduce ITPP, a novel channel-independent architecture for MTPP modeling that decouples event type information using an encoder-decoder framework with an ODE-based backbone. Central to ITPP is a type-aware inverted self-attention mechanism, designed to explicitly model inter-channel correlations among heterogeneous event types. This architecture enhances effectiveness and robustness while reducing overfitting. Comprehensive experiments on multiple real-world and synthetic datasets demonstrate that ITPP consistently outperforms state-of-the-art MTPP models in both predictive accuracy and generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。