Bridging Discrete Marks and Continuous Dynamics: Dual-Path Cross-Interaction for Marked Temporal Point Processes

TL;DR

NEXTPP introduces a dual-path neural framework that integrates discrete event marks and continuous-time dynamics through cross-interaction, significantly improving event sequence prediction accuracy in marked temporal point processes.

Contribution

The paper presents NEXTPP, a novel dual-channel model that combines event mark encoding and continuous evolution, enabling explicit bidirectional interaction for better modeling of marked temporal point processes.

Findings

Outperforms state-of-the-art models on five real-world datasets.

Effectively captures complex dependencies between event types and timing.

Demonstrates robustness across diverse event sequence prediction tasks.

Abstract

Predicting irregularly spaced event sequences with discrete marks poses significant challenges due to the complex, asynchronous dependencies embedded within continuous-time data streams.Existing sequential approaches capture dependencies among event tokens but ignore the continuous evolution between events, while Neural Ordinary Differential Equation (Neural ODE) methods model smooth dynamics yet fail to account for how event types influence future timing.To overcome these limitations, we propose NEXTPP, a dual-channel framework that unifies discrete and continuous representations via Event-granular Neural Evolution with Cross-Interaction for Marked Temporal Point Processes. Specifically, NEXTPP encodes discrete event marks via a self-attention mechanism, simultaneously evolving a latent continuous-time state using a Neural ODE. These parallel streams are then fused through a crossattention module to enable explicit bidirectional interaction between continuous and discrete representations. The fused representations drive the conditional intensity function of the neural Hawkes process, while an iterative thinning sampler is employed to generate future events. Extensive evaluations on five real-world datasets demonstrate that NEXTPP consistently outperforms state-of-the-art models. The source code can be found at https://github.com/AONE-NLP/NEXTPP.