Unified Flow Matching for Long Horizon Event Forecasting

TL;DR

This paper introduces a novel flow matching framework for long horizon event forecasting that models event sequences non-autoregressively, improving accuracy and efficiency over existing methods.

Contribution

It presents a unified, non-autoregressive flow matching approach for marked temporal point processes, enabling coherent long-term event trajectory generation.

Findings

Outperforms autoregressive models in accuracy.

Achieves higher efficiency in event sequence generation.

Demonstrates significant improvements on six real-world benchmarks.

Abstract

Modeling long horizon marked event sequences is a fundamental challenge in many real-world applications, including healthcare, finance, and user behavior modeling. Existing neural temporal point process models are typically autoregressive, predicting the next event one step at a time, which limits their efficiency and leads to error accumulation in long-range forecasting. In this work, we propose a unified flow matching framework for marked temporal point processes that enables non-autoregressive, joint modeling of inter-event times and event types, via continuous and discrete flow matching. By learning continuous-time flows for both components, our method generates coherent long horizon event trajectories without sequential decoding. We evaluate our model on six real-world benchmarks and demonstrate significant improvements over autoregressive and diffusion-based baselines in both accuracy and generation efficiency.