Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events
For researchers and practitioners modeling spatiotemporal events, ARCH provides a unified framework for forecasting, inverse inference, and trajectory recovery, addressing limitations of existing point process models.
Existing spatiotemporal event models struggle with complex distributions and are limited to autoregressive prediction. The authors introduce ARCH, a hierarchical flow matching framework that enables flexible conditioning on arbitrary events, outperforming baselines on both prediction and conditional inference tasks across synthetic and real-world datasets.
Events in spatiotemporal systems are ubiquitous, yet modeling their complex distributions remains challenging. Existing point process models often rely on strong structural assumptions and are typically limited to autoregressive, event-by-event prediction. As a result, they struggle to support broader inference tasks such as inverse inference, trajectory reconstruction, and recovery of missing event locations. We introduce Arbitrarily Conditioned Hierarchical Flows (ARCH), a hierarchical flow matching framework for spatiotemporal event modeling. ARCH is expressive enough to capture complex event distributions while enabling tractable and accurate computation of conditional intensities, which quantify instantaneous event risk. Built on a history-encoder-generative-decoder architecture, ARCH introduces a hybrid masking strategy for flexible conditioning on arbitrary observed events. This enables a unified treatment of forecasting, inverse inference, and partial trajectory recovery within a single framework. Experiments on synthetic and real-world datasets show that ARCH consistently outperforms existing baselines across both prediction and conditional inference tasks.