用异步扩散模型提升时间点过程预测，更准更灵活。
ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processes
- 设计异步噪声调度，早事件生成更快，增强远期预测条件。
- 在基准数据集上同时优化下一时段和事件类型预测，效果领先。
- 可灵活适应不同观测与预测时长，适合长期预测任务。
本文提出一种基于异步噪声调度的扩散模型来建模时间点过程。在扩散过程的每一步，噪声调度将不同尺度的噪声注入数据的不同部分。通过精心设计噪声调度，早期事件生成速度更快，从而为预测更遥远的未来提供更强条件。我们推导出一个目标函数，可有效训练适用于广义噪声调度的模型，基于条件流匹配原理。该方法建模序列中事件潜在表示的联合分布，在基准数据集上实现了下一事件间隔时间和事件类型的最优预测性能。此外，通过调整生成过程的起止点，模型能灵活适应不同长度的观测和预测窗口。最后，在长时序预测任务中，该方法显著优于现有基线方法。
原文摘要 · Abstract (English)
This work introduces a novel approach to modeling temporal point processes using diffusion models with an asynchronous noise schedule. At each step of the diffusion process, the noise schedule injects noise of varying scales into different parts of the data. With a careful design of the noise schedules, earlier events are generated faster than later ones, thus providing stronger conditioning for forecasting the more distant future. We derive an objective to effectively train these models for a general family of noise schedules based on conditional flow matching. Our method models the joint distribution of the latent representations of events in a sequence and achieves state-of-the-art results in predicting both the next inter-event time and event type on benchmark datasets. Additionally, it flexibly accommodates varying lengths of observation and prediction windows in different forecasting settings by adjusting the starting and ending points of the generation process. Finally, our method shows superior performance in long-horizon prediction tasks, outperforming existing baseline methods.
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。