ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processes
This work addresses the problem of accurate and flexible forecasting in temporal point processes for applications like event prediction, with incremental improvements in method design.
The paper tackles modeling temporal point processes by introducing an asynchronous diffusion model with a novel noise schedule that generates earlier events faster to condition future predictions, achieving state-of-the-art results in predicting next inter-event times and event types on benchmark datasets.
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.